Vector control of wind turbine on the basis of the fuzzy selective neural net*

Science.gov (United States)

Engel, E. A.; Kovalev, I. V.; Engel, N. E.

2016-04-01

An article describes vector control of wind turbine based on fuzzy selective neural net. Based on the wind turbine system’s state, the fuzzy selective neural net tracks an maximum power point under random perturbations. Numerical simulations are accomplished to clarify the applicability and advantages of the proposed vector wind turbine’s control on the basis of the fuzzy selective neuronet. The simulation results show that the proposed intelligent control of wind turbine achieves real-time control speed and competitive performance, as compared to a classical control model with PID controllers based on traditional maximum torque control strategy.

Face recognition: Eigenface, elastic matching, and neural nets

International Nuclear Information System (INIS)

Zhang, J.; Lades, M.

1997-01-01

This paper is a comparative study of three recently proposed algorithms for face recognition: eigenface, autoassociation and classification neural nets, and elastic matching. After these algorithms were analyzed under a common statistical decision framework, they were evaluated experimentally on four individual data bases, each with a moderate subject size, and a combined data base with more than a hundred different subjects. Analysis and experimental results indicate that the eigenface algorithm, which is essentially a minimum distance classifier, works well when lighting variation is small. Its performance deteriorates significantly as lighting variation increases. The elastic matching algorithm, on the other hand, is insensitive to lighting, face position, and expression variations and therefore is more versatile. The performance of the autoassociation and classification nets is upper bounded by that of the eigenface but is more difficult to implement in practice

A new neural net approach to robot 3D perception and visuo-motor coordination

Science.gov (United States)

Lee, Sukhan

1992-01-01

A novel neural network approach to robot hand-eye coordination is presented. The approach provides a true sense of visual error servoing, redundant arm configuration control for collision avoidance, and invariant visuo-motor learning under gazing control. A 3-D perception network is introduced to represent the robot internal 3-D metric space in which visual error servoing and arm configuration control are performed. The arm kinematic network performs the bidirectional association between 3-D space arm configurations and joint angles, and enforces the legitimate arm configurations. The arm kinematic net is structured by a radial-based competitive and cooperative network with hierarchical self-organizing learning. The main goal of the present work is to demonstrate that the neural net representation of the robot 3-D perception net serves as an important intermediate functional block connecting robot eyes and arms.

NETS - A NEURAL NETWORK DEVELOPMENT TOOL, VERSION 3.0 (MACINTOSH VERSION)

Science.gov (United States)

Phillips, T. A.

1994-01-01

NETS, A Tool for the Development and Evaluation of Neural Networks, provides a simulation of Neural Network algorithms plus an environment for developing such algorithms. Neural Networks are a class of systems modeled after the human brain. Artificial Neural Networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to brain neurons. Problems which involve pattern matching readily fit the class of problems which NETS is designed to solve. NETS uses the back propagation learning method for all of the networks which it creates. The nodes of a network are usually grouped together into clumps called layers. Generally, a network will have an input layer through which the various environment stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to some features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. NETS allows the user to customize the patterns of connections between layers of a network. NETS also provides features for saving the weight values of a network during the learning process, which allows for more precise control over the learning process. NETS is an interpreter. Its method of execution is the familiar "read-evaluate-print" loop found in interpreted languages such as BASIC and LISP. The user is presented with a prompt which is the simulator's way of asking for input. After a command is issued, NETS will attempt to evaluate the command, which may produce more prompts requesting specific information or an error if the command is not understood. The typical process involved when using NETS consists of translating the problem into a format which uses input/output pairs, designing a network configuration for the problem, and finally training the network with input/output pairs until an acceptable error is reached. NETS

NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification

Directory of Open Access Journals (Sweden)

Min Peng

2016-10-01

Full Text Available Near-infrared (NIR face recognition has attracted increasing attention because of its advantage of illumination invariance. However, traditional face recognition methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN for NIR face recognition (specifically face identification in non-cooperative-user applications. The proposed NIRFaceNet is modified from GoogLeNet, but has a more compact structure designed specifically for the Chinese Academy of Sciences Institute of Automation (CASIA NIR database and can achieve higher identification rates with less training time and less processing time. The experimental results demonstrate that NIRFaceNet has an overall advantage compared to other methods in the NIR face recognition domain when image blur and noise are present. The performance suggests that the proposed NIRFaceNet method may be more suitable for non-cooperative-user applications.

Neural-net based coordinated stabilizing control for the exciter and governor loops of low head hydropower plants

Energy Technology Data Exchange (ETDEWEB)

Djukanovic, M.; Novicevic, M.; Dobrijevic, D.; Babic, B. [Electrical Engineering Inst. Nikola Tesla, Belgrade (Yugoslavia); Sobajic, D.J. [Electric Power Research Inst., Palo Alto, CA (United States); Pao, Y.H. [Case Western Reserve Univ., Cleveland, OH (United States)]|[AI WARE, Inc., Cleveland, OH (United States)

1995-12-01

This paper presents a design technique of a new adaptive optimal controller of the low head hydropower plant using artificial neural networks (ANN). The adaptive controller is to operate in real time to improve the generating unit transients through the exciter input, the guide vane position and the runner blade position. The new design procedure is based on self-organization and the predictive estimation capabilities of neural-nets implemented through the cluster-wise segmented associative memory scheme. The developed neural-net based controller (NNC) whose control signals are adjusted using the on-line measurements, can offer better damping effects for generator oscillations over a wide range of operating conditions than conventional controllers. Digital simulations of hydropower plant equipped with low head Kaplan turbine are performed and the comparisons of conventional excitation-governor control, state-space optimal control and neural-net based control are presented. Results obtained on the non-linear mathematical model demonstrate that the effects of the NNC closely agree with those obtained using the state-space multivariable discrete-time optimal controllers.

Neural net prediction of tokamak plasma disruptions

International Nuclear Information System (INIS)

Hernandez, J.V.; Lin, Z.; Horton, W.; McCool, S.C.

1994-10-01

The computation based on neural net algorithms in predicting minor and major disruptions in TEXT tokamak discharges has been performed. Future values of the fluctuating magnetic signal are predicted based on L past values of the magnetic fluctuation signal, measured by a single Mirnov coil. The time step used (= 0.04ms) corresponds to the experimental data sampling rate. Two kinds of approaches are adopted for the task, the contiguous future prediction and the multi-timescale prediction. Results are shown for comparison. Both networks are trained through the back-propagation algorithm with inertial terms. The degree of this success indicates that the magnetic fluctuations associated with tokamak disruptions may be characterized by a relatively low-dimensional dynamical system

NETS - A NEURAL NETWORK DEVELOPMENT TOOL, VERSION 3.0 (MACHINE INDEPENDENT VERSION)

Science.gov (United States)

Baffes, P. T.

1994-01-01

NETS, A Tool for the Development and Evaluation of Neural Networks, provides a simulation of Neural Network algorithms plus an environment for developing such algorithms. Neural Networks are a class of systems modeled after the human brain. Artificial Neural Networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to brain neurons. Problems which involve pattern matching readily fit the class of problems which NETS is designed to solve. NETS uses the back propagation learning method for all of the networks which it creates. The nodes of a network are usually grouped together into clumps called layers. Generally, a network will have an input layer through which the various environment stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to some features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. NETS allows the user to customize the patterns of connections between layers of a network. NETS also provides features for saving the weight values of a network during the learning process, which allows for more precise control over the learning process. NETS is an interpreter. Its method of execution is the familiar "read-evaluate-print" loop found in interpreted languages such as BASIC and LISP. The user is presented with a prompt which is the simulator's way of asking for input. After a command is issued, NETS will attempt to evaluate the command, which may produce more prompts requesting specific information or an error if the command is not understood. The typical process involved when using NETS consists of translating the problem into a format which uses input/output pairs, designing a network configuration for the problem, and finally training the network with input/output pairs until an acceptable error is reached. NETS

Salient regions detection using convolutional neural networks and color volume

Science.gov (United States)

Liu, Guang-Hai; Hou, Yingkun

2018-03-01

Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

Unfolding code for neutron spectrometry based on neural nets technology

International Nuclear Information System (INIS)

Ortiz R, J. M.; Vega C, H. R.

2012-10-01

The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Neural Networks have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This unfolding code called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks was designed in a graphical interface under LabVIEW programming environment. The core of the code is an embedded neural network architecture, previously optimized by the R obust Design of Artificial Neural Networks Methodology . The main features of the code are: is easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6 Lil(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, only seven rate counts measurement with a Bonner spheres spectrometer are required for simultaneously unfold the 60 energy bins of the neutron spectrum and to calculate 15 dosimetric quantities, for radiation protection porpoises. This code generates a full report in html format with all relevant information. (Author)

Neural net generated seismic facies map and attribute facies map

International Nuclear Information System (INIS)

Addy, S.K.; Neri, P.

1998-01-01

The usefulness of 'seismic facies maps' in the analysis of an Upper Wilcox channel system in a 3-D survey shot by CGG in 1995 in Lavaca county in south Texas was discussed. A neural net-generated seismic facies map is a quick hydrocarbon exploration tool that can be applied regionally as well as on a prospect scale. The new technology is used to classify a constant interval parallel to a horizon in a 3-D seismic volume based on the shape of the wiggle traces using a neural network technology. The tool makes it possible to interpret sedimentary features of a petroleum deposit. The same technology can be used in regional mapping by making 'attribute facies maps' in which various forms of amplitude attributes, phase attributes or frequency attributes can be used

Assessment of the expected construction company’s net profit using neural network and multiple regression models

Directory of Open Access Journals (Sweden)

H.H. Mohamad

2013-09-01

This research aims to develop a mathematical model for assessing the expected net profit of any construction company. To achieve the research objective, four steps were performed. First, the main factors affecting firms’ net profit were identified. Second, pertinent data regarding the net profit factors were collected. Third, two different net profit models were developed using the Multiple Regression (MR and the Neural Network (NN techniques. The validity of the proposed models was also investigated. Finally, the results of both MR and NN models were compared to investigate the predictive capabilities of the two models.

Exemplar-based optical neural net classifier for color pattern recognition

Science.gov (United States)

Yu, Francis T. S.; Uang, Chii-Maw; Yang, Xiangyang

1992-10-01

We present a color exemplar-based neural network that can be used as an optimum image classifier or an associative memory. Color decomposition and composition technique is used for constructing the polychromatic interconnection weight matrix (IWM). The Hamming net algorithm is modified to relax the dynamic range requirement of the spatial light modulator and to reduce the number of iteration cycles in the winner-take-all layer. Computer simulation results demonstrated the feasibility of this approach

Real-time applications of neural nets

International Nuclear Information System (INIS)

Spencer, J.E.

1989-05-01

Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs

Real-time applications of neural nets

International Nuclear Information System (INIS)

Spencer, J.E.

1989-01-01

Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas e.g. improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. In this paper, such issues are considered, examples given and possibilities discussed

Real-time applications of neural nets

Energy Technology Data Exchange (ETDEWEB)

Spencer, J.E.

1989-05-01

Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs.

Unfolding code for neutron spectrometry based on neural nets technology

Energy Technology Data Exchange (ETDEWEB)

Ortiz R, J. M.; Vega C, H. R., E-mail: morvymm@yahoo.com.mx [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica, Apdo. Postal 336, 98000 Zacatecas (Mexico)

2012-10-15

The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Neural Networks have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This unfolding code called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks was designed in a graphical interface under LabVIEW programming environment. The core of the code is an embedded neural network architecture, previously optimized by the {sup R}obust Design of Artificial Neural Networks Methodology{sup .} The main features of the code are: is easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a {sup 6}Lil(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, only seven rate counts measurement with a Bonner spheres spectrometer are required for simultaneously unfold the 60 energy bins of the neutron spectrum and to calculate 15 dosimetric quantities, for radiation protection porpoises. This code generates a full report in html format with all relevant information. (Author)

Bayesian Inference using Neural Net Likelihood Models for Protein Secondary Structure Prediction

Directory of Open Access Journals (Sweden)

Seong-Gon Kim

2011-06-01

Full Text Available Several techniques such as Neural Networks, Genetic Algorithms, Decision Trees and other statistical or heuristic methods have been used to approach the complex non-linear task of predicting Alpha-helicies, Beta-sheets and Turns of a proteins secondary structure in the past. This project introduces a new machine learning method by using an offline trained Multilayered Perceptrons (MLP as the likelihood models within a Bayesian Inference framework to predict secondary structures proteins. Varying window sizes are used to extract neighboring amino acid information and passed back and forth between the Neural Net models and the Bayesian Inference process until there is a convergence of the posterior secondary structure probability.

Neural Net Safety Monitor Design

Science.gov (United States)

Larson, Richard R.

2007-01-01

The National Aeronautics and Space Administration (NASA) at the Dryden Flight Research Center (DFRC) has been conducting flight-test research using an F-15 aircraft (figure 1). This aircraft has been specially modified to interface a neural net (NN) controller as part of a single-string Airborne Research Test System (ARTS) computer with the existing quad-redundant flight control system (FCC) shown in figure 2. The NN commands are passed to FCC channels 2 and 4 and are cross channel data linked (CCDL) to the other computers as shown. Numerous types of fault-detection monitors exist in the FCC when the NN mode is engaged; these monitors would cause an automatic disengagement of the NN in the event of a triggering fault. Unfortunately, these monitors still may not prevent a possible NN hard-over command from coming through to the control laws. Therefore, an additional and unique safety monitor was designed for a single-string source that allows authority at maximum actuator rates but protects the pilot and structural loads against excessive g-limits in the case of a NN hard-over command input. This additional monitor resides in the FCCs and is executed before the control laws are computed. This presentation describes a floating limiter (FL) concept1 that was developed and successfully test-flown for this program (figure 3). The FL computes the rate of change of the NN commands that are input to the FCC from the ARTS. A window is created with upper and lower boundaries, which is constantly floating and trying to stay centered as the NN command rates are changing. The limiter works by only allowing the window to move at a much slower rate than those of the NN commands. Anywhere within the window, however, full rates are allowed. If a rate persists in one direction, it will eventually hit the boundary and be rate-limited to the floating limiter rate. When this happens, a persistent counter begins and after a limit is reached, a NN disengage command is generated. The

Neural net based determination of generator-shedding requirements in electric power systems

Energy Technology Data Exchange (ETDEWEB)

Djukanovic, M [Electrical Engineering Inst. ' Nikola Tesla' , Belgrade (Yugoslavia); Sobajic, D J; Pao, Y -H [Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Electrical Engineering and Applied Physics Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Computer Engineering and Science AI WARE Inc., Cleveland, OH (United States)

1992-09-01

This paper presents an application of artificial neural networks (ANN) in support of a decision-making process by power system operators directed towards the fast stabilisation of multi-machine systems. The proposed approach considers generator shedding as the most effective discrete supplementary control for improving the dynamic performance of faulted power systems and preventing instabilities. The sensitivity of the transient energy function (TEF) with respect to changes in the amount of dropped generation is used during the training phase of ANNs to assess the critical amount of generator shedding required to prevent the loss of synchronism. The learning capabilities of neural nets are used to establish complex mappings between fault information and the amount of generation to be shed, suggesting it as the control signal to the power system operator. (author)

Neural-net disruption predictor in JT-60U

International Nuclear Information System (INIS)

Yoshino, R.

2003-01-01

The prediction of major disruptions caused by the density limit, the plasma current ramp-down with high internal inductance l i , the low density locked mode and the β-limit has been investigated in JT-60U. The concept of 'stability level', newly proposed in this paper to predict the occurrence of a major disruption, is calculated from nine input parameters every 2 ms by the neural network and the start of a major disruption is predicted when the stability level decreases to a certain level, the 'alarm level'. The neural network is trained in two steps. It is first trained with 12 disruptive and six non-disruptive shots (total of 8011 data points). Second, the target output data for 12 disruptive shots are modified and the network is trained again with additional data points generated by the operator. The 'neural-net disruption predictor' obtained has been tested for 300 disruptive shots (128 945 data points) and 1008 non-disruptive shots (982 800 data points) selected from nine years of operation (1991-1999) of JT-60U. Major disruptions except for those caused by the -limit have been predicted with a prediction success rate of 97-98% at 10 ms prior to the disruption and higher than 90% at 30 ms prior to the disruption while the false alarm rate is 2.1% for non-disruptive shots. This prediction performance has been confirmed for 120 disruptive shots (56 163 data points), caused by the density limit, as well as 1032 non-disruptive shots (1004 611 data points) in the last four years of operation (1999-2002) of JT-60U. A careful selection of the input parameters supplied to the network and the newly developed two-step training of the network have reduced the false alarm rate resulting in a considerable improvement of the prediction success rate. (author)

Evaluation of common methods for sampling invertebrate pollinator assemblages: net sampling out-perform pan traps.

Science.gov (United States)

Popic, Tony J; Davila, Yvonne C; Wardle, Glenda M

2013-01-01

Methods for sampling ecological assemblages strive to be efficient, repeatable, and representative. Unknowingly, common methods may be limited in terms of revealing species function and so of less value for comparative studies. The global decline in pollination services has stimulated surveys of flower-visiting invertebrates, using pan traps and net sampling. We explore the relative merits of these two methods in terms of species discovery, quantifying abundance, function, and composition, and responses of species to changing floral resources. Using a spatially-nested design we sampled across a 5000 km(2) area of arid grasslands, including 432 hours of net sampling and 1296 pan trap-days, between June 2010 and July 2011. Net sampling yielded 22% more species and 30% higher abundance than pan traps, and better reflected the spatio-temporal variation of floral resources. Species composition differed significantly between methods; from 436 total species, 25% were sampled by both methods, 50% only by nets, and the remaining 25% only by pans. Apart from being less comprehensive, if pan traps do not sample flower-visitors, the link to pollination is questionable. By contrast, net sampling functionally linked species to pollination through behavioural observations of flower-visitation interaction frequency. Netted specimens are also necessary for evidence of pollen transport. Benefits of net-based sampling outweighed minor differences in overall sampling effort. As pan traps and net sampling methods are not equivalent for sampling invertebrate-flower interactions, we recommend net sampling of invertebrate pollinator assemblages, especially if datasets are intended to document declines in pollination and guide measures to retain this important ecosystem service.

Evaluation of common methods for sampling invertebrate pollinator assemblages: net sampling out-perform pan traps.

Directory of Open Access Journals (Sweden)

Tony J Popic

Full Text Available Methods for sampling ecological assemblages strive to be efficient, repeatable, and representative. Unknowingly, common methods may be limited in terms of revealing species function and so of less value for comparative studies. The global decline in pollination services has stimulated surveys of flower-visiting invertebrates, using pan traps and net sampling. We explore the relative merits of these two methods in terms of species discovery, quantifying abundance, function, and composition, and responses of species to changing floral resources. Using a spatially-nested design we sampled across a 5000 km(2 area of arid grasslands, including 432 hours of net sampling and 1296 pan trap-days, between June 2010 and July 2011. Net sampling yielded 22% more species and 30% higher abundance than pan traps, and better reflected the spatio-temporal variation of floral resources. Species composition differed significantly between methods; from 436 total species, 25% were sampled by both methods, 50% only by nets, and the remaining 25% only by pans. Apart from being less comprehensive, if pan traps do not sample flower-visitors, the link to pollination is questionable. By contrast, net sampling functionally linked species to pollination through behavioural observations of flower-visitation interaction frequency. Netted specimens are also necessary for evidence of pollen transport. Benefits of net-based sampling outweighed minor differences in overall sampling effort. As pan traps and net sampling methods are not equivalent for sampling invertebrate-flower interactions, we recommend net sampling of invertebrate pollinator assemblages, especially if datasets are intended to document declines in pollination and guide measures to retain this important ecosystem service.

Prediction of Disease Causing Non-Synonymous SNPs by the Artificial Neural Network Predictor NetDiseaseSNP

DEFF Research Database (Denmark)

Johansen, Morten Bo; Gonzalez-Izarzugaza, Jose Maria; Brunak, Søren

2013-01-01

We have developed a sequence conservation-based artificial neural network predictor called NetDiseaseSNP which classifies nsSNPs as disease-causing or neutral. Our method uses the excellent alignment generation algorithm of SIFT to identify related sequences and a combination of 31 features...

Accelerator diagnosis and control by Neural Nets

International Nuclear Information System (INIS)

Spencer, J.E.

1989-01-01

Neural Nets (NN) have been described as a solution looking for a problem. In the last conference, Artificial Intelligence (AI) was considered in the accelerator context. While good for local surveillance and control, its use for large complex systems (LCS) was much more restricted. By contrast, NN provide a good metaphor for LCS. It can be argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems, and therefore provide an ideal adaptive control system. Thus, where AI may be good for maintaining a 'golden orbit,' NN should be good for obtaining it via a quantitative approach to 'look and adjust' methods like operator tweaking which use pattern recognition to deal with hardware and software limitations, inaccuracies or errors as well as imprecise knowledge or understanding of effects like annealing and hysteresis. Further, insights from NN allow one to define feasibility conditions for LCS in terms of design constraints and tolerances. Hardware and software implications are discussed and several LCS of current interest are compared and contrasted. 15 refs., 5 figs

Accelerator diagnosis and control by Neural Nets

International Nuclear Information System (INIS)

Spencer, J.E.

1989-01-01

Neural Nets (NN) have been described as a solution looking for a problem. In the last conference, Artificial Intelligence (AI) was considered in the accelerator context. While good for local surveillance and control, its use for large complex systems (LCS) was much more restricted. By contrast, NN provide a good metaphore for LCS. It can be argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems and therefore provide an ideal adaptive control system. Thus, where A1 may be good for maintaining a golden orbit, NN should be good for obtaining it via a quantitative approach to look and adjust methods like operator tweaking which use pattern recognition to deal with hardware and software limitations, inaccuracies or errors as well as imprecise knowledge or understanding of effects like annealing and hysteresis. Further, insights from NN allow one to define feasibility conditions for LCS in terms of design constraints and tolerances. Hardware and software implications are discussed and several LCS of current interest are compared and contrasted. 15 refs., 5 figs

Unlearning in feed-forward multi-nets

NARCIS (Netherlands)

Spaanenburg, L; Kurkova,; Steele, NC; Neruda, R; Karny, M

2001-01-01

Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. Modular neural networks are multi-nets based on an judicious assembly of functionally different parts. This can be viewed as again a monolithic network, but with more complex

Hip fracture risk assessment: artificial neural network outperforms conditional logistic regression in an age- and sex-matched case control study.

Science.gov (United States)

Tseng, Wo-Jan; Hung, Li-Wei; Shieh, Jiann-Shing; Abbod, Maysam F; Lin, Jinn

2013-07-15

Osteoporotic hip fractures with a significant morbidity and excess mortality among the elderly have imposed huge health and economic burdens on societies worldwide. In this age- and sex-matched case control study, we examined the risk factors of hip fractures and assessed the fracture risk by conditional logistic regression (CLR) and ensemble artificial neural network (ANN). The performances of these two classifiers were compared. The study population consisted of 217 pairs (149 women and 68 men) of fractures and controls with an age older than 60 years. All the participants were interviewed with the same standardized questionnaire including questions on 66 risk factors in 12 categories. Univariate CLR analysis was initially conducted to examine the unadjusted odds ratio of all potential risk factors. The significant risk factors were then tested by multivariate analyses. For fracture risk assessment, the participants were randomly divided into modeling and testing datasets for 10-fold cross validation analyses. The predicting models built by CLR and ANN in modeling datasets were applied to testing datasets for generalization study. The performances, including discrimination and calibration, were compared with non-parametric Wilcoxon tests. In univariate CLR analyses, 16 variables achieved significant level, and six of them remained significant in multivariate analyses, including low T score, low BMI, low MMSE score, milk intake, walking difficulty, and significant fall at home. For discrimination, ANN outperformed CLR in both 16- and 6-variable analyses in modeling and testing datasets (p?hip fracture are more personal than environmental. With adequate model construction, ANN may outperform CLR in both discrimination and calibration. ANN seems to have not been developed to its full potential and efforts should be made to improve its performance.

The EB factory project. I. A fast, neural-net-based, general purpose light curve classifier optimized for eclipsing binaries

International Nuclear Information System (INIS)

Paegert, Martin; Stassun, Keivan G.; Burger, Dan M.

2014-01-01

We describe a new neural-net-based light curve classifier and provide it with documentation as a ready-to-use tool for the community. While optimized for identification and classification of eclipsing binary stars, the classifier is general purpose, and has been developed for speed in the context of upcoming massive surveys such as the Large Synoptic Survey Telescope. A challenge for classifiers in the context of neural-net training and massive data sets is to minimize the number of parameters required to describe each light curve. We show that a simple and fast geometric representation that encodes the overall light curve shape, together with a chi-square parameter to capture higher-order morphology information results in efficient yet robust light curve classification, especially for eclipsing binaries. Testing the classifier on the ASAS light curve database, we achieve a retrieval rate of 98% and a false-positive rate of 2% for eclipsing binaries. We achieve similarly high retrieval rates for most other periodic variable-star classes, including RR Lyrae, Mira, and delta Scuti. However, the classifier currently has difficulty discriminating between different sub-classes of eclipsing binaries, and suffers a relatively low (∼60%) retrieval rate for multi-mode delta Cepheid stars. We find that it is imperative to train the classifier's neural network with exemplars that include the full range of light curve quality to which the classifier will be expected to perform; the classifier performs well on noisy light curves only when trained with noisy exemplars. The classifier source code, ancillary programs, a trained neural net, and a guide for use, are provided.

An adaptable Boolean net trainable to control a computing robot

International Nuclear Information System (INIS)

Lauria, F. E.; Prevete, R.; Milo, M.; Visco, S.

1999-01-01

We discuss a method to implement in a Boolean neural network a Hebbian rule so to obtain an adaptable universal control system. We start by presenting both the Boolean neural net and the Hebbian rule we have considered. Then we discuss, first, the problems arising when the latter is naively implemented in a Boolean neural net, second, the method consenting us to overcome them and the ensuing adaptable Boolean neural net paradigm. Next, we present the adaptable Boolean neural net as an intelligent control system, actually controlling a writing robot, and discuss how to train it in the execution of the elementary arithmetic operations on operands represented by numerals with an arbitrary number of digits

Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

Science.gov (United States)

Graves, Alex; Schmidhuber, Jürgen

2005-01-01

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

ConvNetQuake: Convolutional Neural Network for Earthquake Detection and Location

Science.gov (United States)

Denolle, M.; Perol, T.; Gharbi, M.

2017-12-01

Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. In this work, we leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for probabilistic earthquake detection and location from single stations. We apply our technique to study two years of induced seismicity in Oklahoma (USA). We detect 20 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm detection performances are at least one order of magnitude faster than other established methods.

Development of the neural net technique for particle physics. Study of the e+e- → Z0 → γH reaction

International Nuclear Information System (INIS)

Guicheney, C.

1992-01-01

This study is concerned with the application of pattern recognition methods through neural networks to High Energy physics. Two methods, Hopfield nets and multilayer nets, are analyzed and shown to have high potential for (resp.) clusterization and classification. Hopfield nets are used for the recognition of jets occurring during the fragmentation process of the e + e - reaction. Multilayer nets are used for the whole reaction analysis. Impediments are pointed out. Associated background noise is also examined. Multilayer nets may enhance the signal to noise ratio when looking for an upper limit for the production of a Higgs boson in the expected canal, and allow for the specific study of the γ b anti b

Artificial neural net system for interactive tissue classification with MR imaging and image segmentation

International Nuclear Information System (INIS)

Clarke, L.P.; Silbiger, M.; Naylor, C.; Brown, K.

1990-01-01

This paper reports on the development of interactive methods for MR tissue classification that permit mathematically rigorous methods for three-dimensional image segmentation and automatic organ/tumor contouring, as required for surgical and RTP planning. The authors investigate a number of image-intensity based tissue- classification methods that make no implicit assumptions on the MR parameters and hence are not limited by image data set. Similarly, we have trained artificial neural net (ANN) systems for both supervised and unsupervised tissue classification

Three-dimensional neural net for learning visuomotor coordination of a robot arm.

Science.gov (United States)

Martinetz, T M; Ritter, H J; Schulten, K J

1990-01-01

An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm. Learning occurs by a sequence of trial movements without the need for an external teacher. Using input signals from a pair of cameras, the closed robot arm system is able to reduce its positioning error to about 0.3% of the linear dimensions of its work space. This is achieved by choosing the connectivity of a three-dimensional lattice consisting of the units of the neural net.

Neural networks for combined control of capacitor banks and voltage regulators in distribution systems

Energy Technology Data Exchange (ETDEWEB)

Gu, Z.; Rizy, D.T.

1996-02-01

A neural network for controlling shunt capacitor banks and feeder voltage regulators in electric distribution systems is presented. The objective of the neural controller is to minimize total I{sup 2}R losses and maintain all bus voltages within standard limits. The performance of the neural network for different input selections and training data is discussed and compared. Two different input selections are tried, one using the previous control states of the capacitors and regulator along with measured line flows and voltage which is equivalent to having feedback and the other with measured line flows and voltage without previous control settings. The results indicate that the neural net controller with feedback can outperform the one without. Also, proper selection of a training data set that adequately covers the operating space of the distribution system is important for achieving satisfactory performance with the neural controller. The neural controller is tested on a radially configured distribution system with 30 buses, 5 switchable capacitor banks an d one nine tap line regulator to demonstrate the performance characteristics associated with these principles. Monte Carlo simulations show that a carefully designed and relatively compact neural network with a small but carefully developed training set can perform quite well under slight and extreme variation of loading conditions.

Door and cabinet recognition using convolutional neural nets and real-time method fusion for handle detection and grasping

DEFF Research Database (Denmark)

Maurin, Adrian Llopart; Ravn, Ole; Andersen, Nils Axel

2017-01-01

In this paper we present a new method that robustly identifies doors, cabinets and their respective handles, with special emphasis on extracting useful features from handles to be then manipulated. The novelty of this system relies on the combination of a Convolutional Neural Net (CNN), as a form...

A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

Science.gov (United States)

van den Bergh, J.; Schutz, J.; Chirayath, V.; Li, A.

2017-12-01

NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Net's convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign.Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users' input against pre-classified coral imagery to gauge their accuracy and utilizes in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

Science.gov (United States)

van den Bergh, Jarrett; Schutz, Joey; Li, Alan; Chirayath, Ved

2017-01-01

NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Nets convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign. Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users input against pre-classified coral imagery to gauge their accuracy and utilize in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

Single-shot T2 mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network.

Science.gov (United States)

Cai, Congbo; Wang, Chao; Zeng, Yiqing; Cai, Shuhui; Liang, Dong; Wu, Yawen; Chen, Zhong; Ding, Xinghao; Zhong, Jianhui

2018-04-24

An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T 2 mapping from single-shot overlapping-echo detachment (OLED) planar imaging. The training dataset was obtained from simulations that were carried out on SPROM (Simulation with PRoduct Operator Matrix) software developed by our group. The relationship between the original OLED image containing two echo signals and the corresponding T 2 mapping was learned by ResNet training. After the ResNet was trained, it was applied to reconstruct the T 2 mapping from simulation and in vivo human brain data. Although the ResNet was trained entirely on simulated data, the trained network was generalized well to real human brain data. The results from simulation and in vivo human brain experiments show that the proposed method significantly outperforms the echo-detachment-based method. Reliable T 2 mapping with higher accuracy is achieved within 30 ms after the network has been trained, while the echo-detachment-based OLED reconstruction method took approximately 2 min. The proposed method will facilitate real-time dynamic and quantitative MR imaging via OLED sequence, and deep convolutional neural network has the potential to reconstruct maps from complex MRI sequences efficiently. © 2018 International Society for Magnetic Resonance in Medicine.

22nd Italian Workshop on Neural Nets

CERN Document Server

Bassis, Simone; Esposito, Anna; Morabito, Francesco

2013-01-01

This volume collects a selection of contributions which has been presented at the 22nd Italian Workshop on Neural Networks, the yearly meeting of the Italian Society for Neural Networks (SIREN). The conference was held in Italy, Vietri sul Mare (Salerno), during May 17-19, 2012. The annual meeting of SIREN is sponsored by International Neural Network Society (INNS), European Neural Network Society (ENNS) and IEEE Computational Intelligence Society (CIS). The book – as well as the workshop-  is organized in three main components, two special sessions and a group of regular sessions featuring different aspects and point of views of artificial neural networks and natural intelligence, also including applications of present compelling interest.

Net load forecasting for high renewable energy penetration grids

International Nuclear Information System (INIS)

Kaur, Amanpreet; Nonnenmacher, Lukas; Coimbra, Carlos F.M.

2016-01-01

We discuss methods for net load forecasting and their significance for operation and management of power grids with high renewable energy penetration. Net load forecasting is an enabling technology for the integration of microgrid fleets with the macrogrid. Net load represents the load that is traded between the grids (microgrid and utility grid). It is important for resource allocation and electricity market participation at the point of common coupling between the interconnected grids. We compare two inherently different approaches: additive and integrated net load forecast models. The proposed methodologies are validated on a microgrid with 33% annual renewable energy (solar) penetration. A heuristics based solar forecasting technique is proposed, achieving skill of 24.20%. The integrated solar and load forecasting model outperforms the additive model by 10.69% and the uncertainty range for the additive model is larger than the integrated model by 2.2%. Thus, for grid applications an integrated forecast model is recommended. We find that the net load forecast errors and the solar forecasting errors are cointegrated with a common stochastic drift. This is useful for future planning and modeling because the solar energy time-series allows to infer important features of the net load time-series, such as expected variability and uncertainty. - Highlights: • Net load forecasting methods for grids with renewable energy generation are discussed. • Integrated solar and load forecasting outperforms the additive model by 10.69%. • Net load forecasting reduces the uncertainty between the interconnected grids.

REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

Directory of Open Access Journals (Sweden)

S Safinaz

2017-08-01

Full Text Available In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

Proteome Profiling Outperforms Transcriptome Profiling for Coexpression Based Gene Function Prediction

Energy Technology Data Exchange (ETDEWEB)

Wang, Jing; Ma, Zihao; Carr, Steven A.; Mertins, Philipp; Zhang, Hui; Zhang, Zhen; Chan, Daniel W.; Ellis, Matthew J. C.; Townsend, R. Reid; Smith, Richard D.; McDermott, Jason E.; Chen, Xian; Paulovich, Amanda G.; Boja, Emily S.; Mesri, Mehdi; Kinsinger, Christopher R.; Rodriguez, Henry; Rodland, Karin D.; Liebler, Daniel C.; Zhang, Bing

2016-11-11

Coexpression of mRNAs under multiple conditions is commonly used to infer cofunctionality of their gene products despite well-known limitations of this “guilt-by-association” (GBA) approach. Recent advancements in mass spectrometry-based proteomic technologies have enabled global expression profiling at the protein level; however, whether proteome profiling data can outperform transcriptome profiling data for coexpression based gene function prediction has not been systematically investigated. Here, we address this question by constructing and analyzing mRNA and protein coexpression networks for three cancer types with matched mRNA and protein profiling data from The Cancer Genome Atlas (TCGA) and the Clinical Proteomic Tumor Analysis Consortium (CPTAC). Our analyses revealed a marked difference in wiring between the mRNA and protein coexpression networks. Whereas protein coexpression was driven primarily by functional similarity between coexpressed genes, mRNA coexpression was driven by both cofunction and chromosomal colocalization of the genes. Functionally coherent mRNA modules were more likely to have their edges preserved in corresponding protein networks than functionally incoherent mRNA modules. Proteomic data strengthened the link between gene expression and function for at least 75% of Gene Ontology (GO) biological processes and 90% of KEGG pathways. A web application Gene2Net (http://cptac.gene2net.org) developed based on the three protein coexpression networks revealed novel gene-function relationships, such as linking ERBB2 (HER2) to lipid biosynthetic process in breast cancer, identifying PLG as a new gene involved in complement activation, and identifying AEBP1 as a new epithelial-mesenchymal transition (EMT) marker. Our results demonstrate that proteome profiling outperforms transcriptome profiling for coexpression based gene function prediction. Proteomics should be integrated if not preferred in gene function and human disease studies

NetTurnP – Neural Network Prediction of Beta-turns by Use of Evolutionary Information and Predicted Protein Sequence Features

DEFF Research Database (Denmark)

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-01-01

is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino......β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method...... NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which...

NutriNet: A Deep Learning Food and Drink Image Recognition System for Dietary Assessment.

Science.gov (United States)

Mezgec, Simon; Koroušić Seljak, Barbara

2017-06-27

Automatic food image recognition systems are alleviating the process of food-intake estimation and dietary assessment. However, due to the nature of food images, their recognition is a particularly challenging task, which is why traditional approaches in the field have achieved a low classification accuracy. Deep neural networks have outperformed such solutions, and we present a novel approach to the problem of food and drink image detection and recognition that uses a newly-defined deep convolutional neural network architecture, called NutriNet. This architecture was tuned on a recognition dataset containing 225,953 512 × 512 pixel images of 520 different food and drink items from a broad spectrum of food groups, on which we achieved a classification accuracy of 86 . 72 % , along with an accuracy of 94 . 47 % on a detection dataset containing 130 , 517 images. We also performed a real-world test on a dataset of self-acquired images, combined with images from Parkinson's disease patients, all taken using a smartphone camera, achieving a top-five accuracy of 55 % , which is an encouraging result for real-world images. Additionally, we tested NutriNet on the University of Milano-Bicocca 2016 (UNIMIB2016) food image dataset, on which we improved upon the provided baseline recognition result. An online training component was implemented to continually fine-tune the food and drink recognition model on new images. The model is being used in practice as part of a mobile app for the dietary assessment of Parkinson's disease patients.

NetTurnP--neural network prediction of beta-turns by use of evolutionary information and predicted protein sequence features.

Directory of Open Access Journals (Sweden)

Bent Petersen

Full Text Available UNLABELLED: β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. CONCLUSION: The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.

NetTurnP--neural network prediction of beta-turns by use of evolutionary information and predicted protein sequence features.

Science.gov (United States)

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-11-30

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.

Estimação do volume de árvores utilizando redes neurais artificiais Estimate of tree volume using artificial neural nets

Directory of Open Access Journals (Sweden)

Eric Bastos Gorgens

2009-12-01

Full Text Available Rede neural artificial consiste em um conjunto de unidades que contêm funções matemáticas, unidas por pesos. As redes são capazes de aprender, mediante modificação dos pesos sinápticos, e generalizar o aprendizado para outros arquivos desconhecidos. O projeto de redes neurais é composto por três etapas: pré-processamento, processamento e, por fim, pós-processamento dos dados. Um dos problemas clássicos que podem ser abordados por redes é a aproximação de funções. Nesse grupo, pode-se incluir a estimação do volume de árvores. Foram utilizados quatro arquiteturas diferentes, cinco pré-processamentos e duas funções de ativação. As redes que se apresentaram estatisticamente iguais aos dados observados também foram analisadas quanto ao resíduo e à distribuição dos volumes e comparadas com a estimação de volume pelo modelo de Schumacher e Hall. As redes neurais formadas por neurônios, cuja função de ativação era exponencial, apresentaram estimativas estatisticamente iguais aos dados observados. As redes treinadas com os dados normalizados pelo método da interpolação linear e equalizados tiveram melhor desempenho na estimação.The artificial neural network consists of a set of units containing mathematical functions connected by weights. Such nets are capable of learning by means of synaptic weight modification, generalizing learning for other unknown archives. The neural network project comprises three stages: pre-processing, processing and post-processing of data. One of the classical problems approached by networks is function approximation. Tree volume estimate can be included in this group. Four different architectures, five pre-processings and two activation functions were used. The nets which were statistically similar to the observed data were also analyzed in relation to residue and volume and compared to the volume estimate provided by the Schumacher and Hall equation. The neural nets formed by

Neural network signal understanding for instrumentation

DEFF Research Database (Denmark)

Pau, L. F.; Johansen, F. S.

1990-01-01

understanding research is surveyed, and the selected implementation and its performance in terms of correct classification rates and robustness to noise are described. Formal results on neural net training time and sensitivity to weights are given. A theory for neural control using functional link nets is given...

Shakeout: A New Approach to Regularized Deep Neural Network Training.

Science.gov (United States)

Kang, Guoliang; Li, Jun; Tao, Dacheng

2018-05-01

Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines , and regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

Musical Audio Synthesis Using Autoencoding Neural Nets

OpenAIRE

Sarroff, Andy; Casey, Michael A.

2014-01-01

With an optimal network topology and tuning of hyperpa-\\ud rameters, artificial neural networks (ANNs) may be trained\\ud to learn a mapping from low level audio features to one\\ud or more higher-level representations. Such artificial neu-\\ud ral networks are commonly used in classification and re-\\ud gression settings to perform arbitrary tasks. In this work\\ud we suggest repurposing autoencoding neural networks as\\ud musical audio synthesizers. We offer an interactive musi-\\ud cal audio synt...

A deep convolutional neural network for recognizing foods

Science.gov (United States)

Jahani Heravi, Elnaz; Habibi Aghdam, Hamed; Puig, Domenec

2015-12-01

Controlling the food intake is an efficient way that each person can undertake to tackle the obesity problem in countries worldwide. This is achievable by developing a smartphone application that is able to recognize foods and compute their calories. State-of-art methods are chiefly based on hand-crafted feature extraction methods such as HOG and Gabor. Recent advances in large-scale object recognition datasets such as ImageNet have revealed that deep Convolutional Neural Networks (CNN) possess more representation power than the hand-crafted features. The main challenge with CNNs is to find the appropriate architecture for each problem. In this paper, we propose a deep CNN which consists of 769; 988 parameters. Our experiments show that the proposed CNN outperforms the state-of-art methods and improves the best result of traditional methods 17%. Moreover, using an ensemble of two CNNs that have been trained two different times, we are able to improve the classification performance 21:5%.

The gamma model : a new neural network for temporal processing

NARCIS (Netherlands)

Vries, de B.

1992-01-01

In this paper we develop the gamma neural model, a new neural net architecture for processing of temporal patterns. Time varying patterns are normally segmented into a sequence of static patterns that are successively presented to a neural net. In the approach presented here segmentation is avoided.

ANT Advanced Neural Tool

Energy Technology Data Exchange (ETDEWEB)

Labrador, I.; Carrasco, R.; Martinez, L.

1996-07-01

This paper describes a practical introduction to the use of Artificial Neural Networks. Artificial Neural Nets are often used as an alternative to the traditional symbolic manipulation and first order logic used in Artificial Intelligence, due the high degree of difficulty to solve problems that can not be handled by programmers using algorithmic strategies. As a particular case of Neural Net a Multilayer Perception developed by programming in C language on OS9 real time operating system is presented. A detailed description about the program structure and practical use are included. Finally, several application examples that have been treated with the tool are presented, and some suggestions about hardware implementations. (Author) 15 refs.

ANT Advanced Neural Tool

International Nuclear Information System (INIS)

Labrador, I.; Carrasco, R.; Martinez, L.

1996-01-01

This paper describes a practical introduction to the use of Artificial Neural Networks. Artificial Neural Nets are often used as an alternative to the traditional symbolic manipulation and first order logic used in Artificial Intelligence, due the high degree of difficulty to solve problems that can not be handled by programmers using algorithmic strategies. As a particular case of Neural Net a Multilayer Perception developed by programming in C language on OS9 real time operating system is presented. A detailed description about the program structure and practical use are included. Finally, several application examples that have been treated with the tool are presented, and some suggestions about hardware implementations. (Author) 15 refs

Neural networks for aircraft control

Science.gov (United States)

Linse, Dennis

1990-01-01

Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

VP-Nets : Efficient automatic localization of key brain structures in 3D fetal neurosonography.

Science.gov (United States)

Huang, Ruobing; Xie, Weidi; Alison Noble, J

2018-04-23

Three-dimensional (3D) fetal neurosonography is used clinically to detect cerebral abnormalities and to assess growth in the developing brain. However, manual identification of key brain structures in 3D ultrasound images requires expertise to perform and even then is tedious. Inspired by how sonographers view and interact with volumes during real-time clinical scanning, we propose an efficient automatic method to simultaneously localize multiple brain structures in 3D fetal neurosonography. The proposed View-based Projection Networks (VP-Nets), uses three view-based Convolutional Neural Networks (CNNs), to simplify 3D localizations by directly predicting 2D projections of the key structures onto three anatomical views. While designed for efficient use of data and GPU memory, the proposed VP-Nets allows for full-resolution 3D prediction. We investigated parameters that influence the performance of VP-Nets, e.g. depth and number of feature channels. Moreover, we demonstrate that the model can pinpoint the structure in 3D space by visualizing the trained VP-Nets, despite only 2D supervision being provided for a single stream during training. For comparison, we implemented two other baseline solutions based on Random Forest and 3D U-Nets. In the reported experiments, VP-Nets consistently outperformed other methods on localization. To test the importance of loss function, two identical models are trained with binary corss-entropy and dice coefficient loss respectively. Our best VP-Net model achieved prediction center deviation: 1.8 ± 1.4 mm, size difference: 1.9 ± 1.5 mm, and 3D Intersection Over Union (IOU): 63.2 ± 14.7% when compared to the ground truth. To make the whole pipeline intervention free, we also implement a skull-stripping tool using 3D CNN, which achieves high segmentation accuracy. As a result, the proposed processing pipeline takes a raw ultrasound brain image as input, and output a skull-stripped image with five detected key brain

Automated target recognition and tracking using an optical pattern recognition neural network

Science.gov (United States)

Chao, Tien-Hsin

1991-01-01

The on-going development of an automatic target recognition and tracking system at the Jet Propulsion Laboratory is presented. This system is an optical pattern recognition neural network (OPRNN) that is an integration of an innovative optical parallel processor and a feature extraction based neural net training algorithm. The parallel optical processor provides high speed and vast parallelism as well as full shift invariance. The neural network algorithm enables simultaneous discrimination of multiple noisy targets in spite of their scales, rotations, perspectives, and various deformations. This fully developed OPRNN system can be effectively utilized for the automated spacecraft recognition and tracking that will lead to success in the Automated Rendezvous and Capture (AR&C) of the unmanned Cargo Transfer Vehicle (CTV). One of the most powerful optical parallel processors for automatic target recognition is the multichannel correlator. With the inherent advantages of parallel processing capability and shift invariance, multiple objects can be simultaneously recognized and tracked using this multichannel correlator. This target tracking capability can be greatly enhanced by utilizing a powerful feature extraction based neural network training algorithm such as the neocognitron. The OPRNN, currently under investigation at JPL, is constructed with an optical multichannel correlator where holographic filters have been prepared using the neocognitron training algorithm. The computation speed of the neocognitron-type OPRNN is up to 10(exp 14) analog connections/sec that enabling the OPRNN to outperform its state-of-the-art electronics counterpart by at least two orders of magnitude.

NetPhosYeast: prediction of protein phosphorylation sites in yeast

DEFF Research Database (Denmark)

Ingrell, C.R.; Miller, Martin Lee; Jensen, O.N.

2007-01-01

sites compared to those in humans, suggesting the need for an yeast-specific phosphorylation site predictor. NetPhosYeast achieves a correlation coefficient close to 0.75 with a sensitivity of 0.84 and specificity of 0.90 and outperforms existing predictors in the identification of phosphorylation sites...

NetTurnP – Neural Network Prediction of Beta-turns by Use of Evolutionary Information and Predicted Protein Sequence Features

Science.gov (United States)

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-01-01

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC  = 0.50, Qtotal = 82.1%, sensitivity  = 75.6%, PPV  = 68.8% and AUC  = 0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17 – 0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. Conclusion The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences. PMID:21152409

Schema generation in recurrent neural nets for intercepting a moving target.

Science.gov (United States)

Fleischer, Andreas G

2010-06-01

The grasping of a moving object requires the development of a motor strategy to anticipate the trajectory of the target and to compute an optimal course of interception. During the performance of perception-action cycles, a preprogrammed prototypical movement trajectory, a motor schema, may highly reduce the control load. Subjects were asked to hit a target that was moving along a circular path by means of a cursor. Randomized initial target positions and velocities were detected in the periphery of the eyes, resulting in a saccade toward the target. Even when the target disappeared, the eyes followed the target's anticipated course. The Gestalt of the trajectories was dependent on target velocity. The prediction capability of the motor schema was investigated by varying the visibility range of cursor and target. Motor schemata were determined to be of limited precision, and therefore visual feedback was continuously required to intercept the moving target. To intercept a target, the motor schema caused the hand to aim ahead and to adapt to the target trajectory. The control of cursor velocity determined the point of interception. From a modeling point of view, a neural network was developed that allowed the implementation of a motor schema interacting with feedback control in an iterative manner. The neural net of the Wilson type consists of an excitation-diffusion layer allowing the generation of a moving bubble. This activation bubble runs down an eye-centered motor schema and causes a planar arm model to move toward the target. A bubble provides local integration and straightening of the trajectory during repetitive moves. The schema adapts to task demands by learning and serves as forward controller. On the basis of these model considerations the principal problem of embedding motor schemata in generalized control strategies is discussed.

Enhancing ASR by MT using Semantic Information from HindiWordNet

DEFF Research Database (Denmark)

Tammewar, Aniruddha; Singla, Karan; Bangalore, Srinivas

translation. We report several experiments to improve the performance of an automatic speech recognition system, taking advantage of machine translation output and information fromWordNet. Overall we outperform a baseline system which has no semantic information by an increased 1.6% word accuracy...

Larger bases and mixed analog/digital neural nets

Energy Technology Data Exchange (ETDEWEB)

Beiu, V.

1998-12-31

The paper overviews results dealing with the approximation capabilities of neural networks, and bounds on the size of threshold gate circuits. Based on an explicit numerical algorithm for Kolmogorov`s superpositions the authors show that minimum size neural networks--for implementing any Boolean function--have the identity function as the activation function. Conclusions and several comments on the required precision are ending the paper.

Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks

Directory of Open Access Journals (Sweden)

Emilio Granell

2018-01-01

Full Text Available The digitization of historical handwritten document images is important for the preservation of cultural heritage. Moreover, the transcription of text images obtained from digitization is necessary to provide efficient information access to the content of these documents. Handwritten Text Recognition (HTR has become an important research topic in the areas of image and computational language processing that allows us to obtain transcriptions from text images. State-of-the-art HTR systems are, however, far from perfect. One difficulty is that they have to cope with image noise and handwriting variability. Another difficulty is the presence of a large amount of Out-Of-Vocabulary (OOV words in ancient historical texts. A solution to this problem is to use external lexical resources, but such resources might be scarce or unavailable given the nature and the age of such documents. This work proposes a solution to avoid this limitation. It consists of associating a powerful optical recognition system that will cope with image noise and variability, with a language model based on sub-lexical units that will model OOV words. Such a language modeling approach reduces the size of the lexicon while increasing the lexicon coverage. Experiments are first conducted on the publicly available Rodrigo dataset, which contains the digitization of an ancient Spanish manuscript, with a recognizer based on Hidden Markov Models (HMMs. They show that sub-lexical units outperform word units in terms of Word Error Rate (WER, Character Error Rate (CER and OOV word accuracy rate. This approach is then applied to deep net classifiers, namely Bi-directional Long-Short Term Memory (BLSTMs and Convolutional Recurrent Neural Nets (CRNNs. Results show that CRNNs outperform HMMs and BLSTMs, reaching the lowest WER and CER for this image dataset and significantly improving OOV recognition.

2D neural hardware versus 3D biological ones

Energy Technology Data Exchange (ETDEWEB)

Beiu, V.

1998-12-31

This paper will present important limitations of hardware neural nets as opposed to biological neural nets (i.e. the real ones). The author starts by discussing neural structures and their biological inspirations, while mentioning the simplifications leading to artificial neural nets. Going further, the focus will be on hardware constraints. The author will present recent results for three different alternatives of implementing neural networks: digital, threshold gate, and analog, while the area and the delay will be related to neurons' fan-in and weights' precision. Based on all of these, it will be shown why hardware implementations cannot cope with their biological inspiration with respect to their power of computation: the mapping onto silicon lacking the third dimension of biological nets. This translates into reduced fan-in, and leads to reduced precision. The main conclusion is that one is faced with the following alternatives: (1) try to cope with the limitations imposed by silicon, by speeding up the computation of the elementary silicon neurons; (2) investigate solutions which would allow one to use the third dimension, e.g. using optical interconnections.

Do neural nets learn statistical laws behind natural language?

Directory of Open Access Journals (Sweden)

Shuntaro Takahashi

Full Text Available The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM effectively reproduces Zipf's law and Heaps' law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf's law and Heaps' law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks.

On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation

OpenAIRE

He, Tianxing; Zhang, Yu; Droppo, Jasha; Yu, Kai

2016-01-01

We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It is shown that NCE-trained bi-directional NNLM outperformed the one trained by conventional maximum likelihood training. But still(regretfully), it did not out-perform the baseline uni-directional NNLM.

End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

Science.gov (United States)

Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

2017-12-01

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Reconstruction of neutron spectra through neural networks

International Nuclear Information System (INIS)

Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.

2003-01-01

A neural network has been used to reconstruct the neutron spectra starting from the counting rates of the detectors of the Bonner sphere spectrophotometric system. A group of 56 neutron spectra was selected to calculate the counting rates that would produce in a Bonner sphere system, with these data and the spectra it was trained the neural network. To prove the performance of the net, 12 spectra were used, 6 were taken of the group used for the training, 3 were obtained of mathematical functions and those other 3 correspond to real spectra. When comparing the original spectra of those reconstructed by the net we find that our net has a poor performance when reconstructing monoenergetic spectra, this attributes it to those characteristic of the spectra used for the training of the neural network, however for the other groups of spectra the results of the net are appropriate with the prospective ones. (Author)

Tutorial on neural network applications in high energy physics: A 1992 perspective

International Nuclear Information System (INIS)

Denby, B.

1992-04-01

Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given

Universal approximation in p-mean by neural networks

NARCIS (Netherlands)

Burton, R.M; Dehling, H.G

A feedforward neural net with d input neurons and with a single hidden layer of n neurons is given by [GRAPHICS] where a(j), theta(j), w(ji) is an element of R. In this paper we study the approximation of arbitrary functions f: R-d --> R by a neural net in an L-p(mu) norm for some finite measure mu

A bat's ear view of neural nets in physics

International Nuclear Information System (INIS)

Denby, B.

1997-01-01

The use of neural networks in high energy physics has become a field of its own which now has been in existence for ten years. This paper attempts to draw some conclusions on the utility of neural networks for physics applications, and also to make some projections for the future of this line of research. (orig.)

Parallel consensual neural networks.

Science.gov (United States)

Benediktsson, J A; Sveinsson, J R; Ersoy, O K; Swain, P H

1997-01-01

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

Goal-seeking neural net for recall and recognition

Science.gov (United States)

Omidvar, Omid M.

1990-07-01

Neural networks have been used to mimic cognitive processes which take place in animal brains. The learning capability inherent in neural networks makes them suitable candidates for adaptive tasks such as recall and recognition. The synaptic reinforcements create a proper condition for adaptation, which results in memorization, formation of perception, and higher order information processing activities. In this research a model of a goal seeking neural network is studied and the operation of the network with regard to recall and recognition is analyzed. In these analyses recall is defined as retrieval of stored information where little or no matching is involved. On the other hand recognition is recall with matching; therefore it involves memorizing a piece of information with complete presentation. This research takes the generalized view of reinforcement in which all the signals are potential reinforcers. The neuronal response is considered to be the source of the reinforcement. This local approach to adaptation leads to the goal seeking nature of the neurons as network components. In the proposed model all the synaptic strengths are reinforced in parallel while the reinforcement among the layers is done in a distributed fashion and pipeline mode from the last layer inward. A model of complex neuron with varying threshold is developed to account for inhibitory and excitatory behavior of real neuron. A goal seeking model of a neural network is presented. This network is utilized to perform recall and recognition tasks. The performance of the model with regard to the assigned tasks is presented.

EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation.

Science.gov (United States)

Amidi, Afshine; Amidi, Shervine; Vlachakis, Dimitrios; Megalooikonomou, Vasileios; Paragios, Nikos; Zacharaki, Evangelia I

2018-01-01

During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank (PDB) has increased more than 15-fold since 1999, which enabled the expansion of models that aim at predicting enzymatic function via their amino acid composition. Amino acid sequence, however, is less conserved in nature than protein structure and therefore considered a less reliable predictor of protein function. This paper presents EnzyNet, a novel 3D convolutional neural networks classifier that predicts the Enzyme Commission number of enzymes based only on their voxel-based spatial structure. The spatial distribution of biochemical properties was also examined as complementary information. The two-layer architecture was investigated on a large dataset of 63,558 enzymes from the PDB and achieved an accuracy of 78.4% by exploiting only the binary representation of the protein shape. Code and datasets are available at https://github.com/shervinea/enzynet.

M&E-NetPay: A Micropayment System for Mobile and Electronic Commerce

Directory of Open Access Journals (Sweden)

Xiaodi Huang

2016-08-01

Full Text Available As an increasing number of people purchase goods and services online, micropayment systems are becoming particularly important for mobile and electronic commerce. We have designed and developed such a system called M&E-NetPay (Mobile and Electronic NetPay. With open interoperability and mobility, M&E-NetPay uses web services to connect brokers and vendors, providing secure, flexible and reliable credit services over the Internet. In particular, M&E-NetPay makes use of a secure, inexpensive and debit-based off-line protocol that allows vendors to interact only with customers, after validating coins. The design of the architecture and protocol of M&E-NetPay are presented, together with the implementation of its prototype in ringtone and wallpaper sites. To validate our system, we have conducted its evaluations on performance, usability and heuristics. Furthermore, we compare our system to the CORBA-based (Common Object Request Broker Architecture off-line micro-payment systems. The results have demonstrated that M&E-NetPay outperforms the .NET-based M&E-NetPay system in terms of performance and user satisfaction.

Using machine learning, neural networks and statistics to predict bankruptcy

NARCIS (Netherlands)

Pompe, P.P.M.; Feelders, A.J.; Feelders, A.J.

1997-01-01

Recent literature strongly suggests that machine learning approaches to classification outperform "classical" statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees, and neural networks in predicting corporate bankruptcy. Linear

Turkey's net energy consumption

International Nuclear Information System (INIS)

Soezen, Adnan; Arcaklioglu, Erol; Oezkaymak, Mehmet

2005-01-01

The main goal of this study is to develop the equations for forecasting net energy consumption (NEC) using an artificial neural-network (ANN) technique in order to determine the future level of energy consumption in Turkey. In this study, two different models were used in order to train the neural network. In one of them, population, gross generation, installed capacity and years are used in the input layer of the network (Model 1). Other energy sources are used in input layer of network (Model 2). The net energy consumption is in the output layer for two models. Data from 1975 to 2003 are used for the training. Three years (1981, 1994 and 2003) are used only as test data to confirm this method. The statistical coefficients of multiple determinations (R 2 -value) for training data are equal to 0.99944 and 0.99913 for Models 1 and 2, respectively. Similarly, R 2 values for testing data are equal to 0.997386 and 0.999558 for Models 1 and 2, respectively. According to the results, the net energy consumption using the ANN technique has been predicted with acceptable accuracy. Apart from reducing the whole time required, with the ANN approach, it is possible to find solutions that make energy applications more viable and thus more attractive to potential users. It is also expected that this study will be helpful in developing highly applicable energy policies

Neural Network for Image-to-Image Control of Optical Tweezers

Science.gov (United States)

Decker, Arthur J.; Anderson, Robert C.; Weiland, Kenneth E.; Wrbanek, Susan Y.

2004-01-01

A method is discussed for using neural networks to control optical tweezers. Neural-net outputs are combined with scaling and tiling to generate 480 by 480-pixel control patterns for a spatial light modulator (SLM). The SLM can be combined in various ways with a microscope to create movable tweezers traps with controllable profiles. The neural nets are intended to respond to scattered light from carbon and silicon carbide nanotube sensors. The nanotube sensors are to be held by the traps for manipulation and calibration. Scaling and tiling allow the 100 by 100-pixel maximum resolution of the neural-net software to be applied in stages to exploit the full 480 by 480-pixel resolution of the SLM. One of these stages is intended to create sensitive null detectors for detecting variations in the scattered light from the nanotube sensors.

MosquitoNet: investigating the use of UAV and artificial neural networks for integrated mosquito management

Science.gov (United States)

Case, E.; Ren, Y.; Shragai, T.; Erickson, D.

2017-12-01

Integrated mosquito control is expensive and resource intensive, and changing climatic factors are predicted to expand the habitable range of disease-carrying mosquitoes into new regions in the United States. Of particular concern in the northeastern United States are aedes albopictus, an aggressive, invasive species of mosquito that can transmit both native and exotic disease. Ae. albopictus prefer to live near human populations and breed in artificial containers with as little as two millimeters of standing water, exponentially increasing the difficulty of source control in suburban and urban areas. However, low-cost unmanned aerial vehicles (UAVs) can be used to photograph large regions at centimeter-resolution, and can image containers of interest in suburban neighborhoods. While proofs-of-concepts have been shown using UAVs to identify naturally occurring bodies of water, they have not been used to identify mosquito habitat in more populated areas. One of the primary challenges is that post-processing high-resolution aerial imagery is still time intensive, often labelled by hand or with programs built for satellite imagery. Artificial neural networks have been highly successful at image recognition tasks; in the past five years, convolutional neural networks (CNN) have surpassed or aided trained humans in identification of skin cancer, agricultural crops, and poverty levels from satellite imagery. MosquitoNet, a dual classifier built from the Single Shot Multibox Detector and VGG16 architectures, was trained on UAV­­­­­ aerial imagery taken during a larval study in Westchester County in southern New York State in July and August 2017. MosquitoNet was designed to assess the habitat risk of suburban properties by automating the identification and counting of containers like tires, toys, garbage bins, flower pots, etc. The SSD-based architecture marked small containers and other habitat indicators while the VGG16-based architecture classified the type of

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set.

Science.gov (United States)

Lenselink, Eelke B; Ten Dijke, Niels; Bongers, Brandon; Papadatos, George; van Vlijmen, Herman W T; Kowalczyk, Wojtek; IJzerman, Adriaan P; van Westen, Gerard J P

2017-08-14

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi

Comparisons of a Quantum Annealing and Classical Computer Neural Net Approach for Inferring Global Annual CO2 Fluxes over Land

Science.gov (United States)

Halem, M.; Radov, A.; Singh, D.

2017-12-01

Investigations of mid to high latitude atmospheric CO2 show growing amplitudes in seasonal variations over the past several decades. Recent high-resolution satellite measurements of CO2 concentration are now available for three years from the Orbiting Carbon Observatory-2. The Atmospheric Radiation Measurement (ARM) program of DOE has been making long-term CO2-flux measurements (in addition to CO2 concentration and an array of other meteorological quantities) at several towers and mobile sites located around the globe at half-hour frequencies. Recent papers have shown CO2 fluxes inferred by assimilating CO2 observations into ecosystem models are largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks. Thus, new approaches for calculating CO2-flux for assimilation into land surface models are necessary for improving the prediction of annual carbon uptake. In this study, we calculate and compare the predicted CO2 fluxes results employing a Feed Forward Backward Propagation Neural Network model on two architectures, (i) an IBM Minsky Computer node and (ii) a hybrid version of the ARC D-Wave quantum annealing computer. We compare the neural net results of predictions of CO2 flux from ARM station data for three different DOE ecosystem sites; an arid plains near Oklahoma City, a northern arctic site at Barrows AL, and a tropical rainforest site in the Amazon. Training times and predictive results for the calculating annual CO2 flux for the two architectures for each of the three sites are presented. Comparative results of predictions as measured by RMSE and MAE are discussed. Plots and correlations of observed vs predicted CO2 flux are also presented for all three sites. We show the estimated training times for quantum and classical calculations when extended to calculating global annual Carbon Uptake over land. We also

Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.

Science.gov (United States)

Korfiatis, Panagiotis; Kline, Timothy L; Lachance, Daniel H; Parney, Ian F; Buckner, Jan C; Erickson, Bradley J

2017-10-01

Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate their ability in predicting MGMT methylation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture was the best performing model, achieving an accuracy of 94.90% (+/- 3.92%) for the test set (classification of a slice as no tumor, methylated MGMT, or non-methylated). ResNet34 (34 layers) achieved 80.72% (+/- 13.61%) while ResNet18 (18 layers) accuracy was 76.75% (+/- 20.67%). ResNet50 performance was statistically significantly better than both ResNet18 and ResNet34 architectures (p deep neural architectures can be used to predict molecular biomarkers from routine medical images.

Smiling on the Inside: The Social Benefits of Suppressing Positive Emotions in Outperformance Situations.

Science.gov (United States)

Schall, Marina; Martiny, Sarah E; Goetz, Thomas; Hall, Nathan C

2016-05-01

Although expressing positive emotions is typically socially rewarded, in the present work, we predicted that people suppress positive emotions and thereby experience social benefits when outperformed others are present. We tested our predictions in three experimental studies with high school students. In Studies 1 and 2, we manipulated the type of social situation (outperformance vs. non-outperformance) and assessed suppression of positive emotions. In both studies, individuals reported suppressing positive emotions more in outperformance situations than in non-outperformance situations. In Study 3, we manipulated the social situation (outperformance vs. non-outperformance) as well as the videotaped person's expression of positive emotions (suppression vs. expression). The findings showed that when outperforming others, individuals were indeed evaluated more positively when they suppressed rather than expressed their positive emotions, and demonstrate the importance of the specific social situation with respect to the effects of suppression. © 2016 by the Society for Personality and Social Psychology, Inc.

A Restricted Boltzman Neural Net to Infer Carbon Uptake from OCO-2 Satellite Data

Science.gov (United States)

Halem, M.; Dorband, J. E.; Radov, A.; Barr-Dallas, M.; Gentine, P.

2015-12-01

For several decades, scientists have been using satellite observations to infer climate budgets of terrestrial carbon uptake employing inverse methods in conjunction with ecosystem models and coupled global climate models. This is an extremely important Big Data calculation today since the net annual photosynthetic carbon uptake changes annually over land and removes on average ~20% of the emissions from human contributions to atmospheric loading of CO2 from fossil fuels. Unfortunately, such calculations have large uncertainties validated with in-situ networks of measuring stations across the globe. One difficulty in using satellite data for these budget calculations is that the models need to assimilate surface fluxes of CO2 as well as soil moisture, vegatation cover and the eddy covariance of latent and sensible heat to calculate the carbon fixed in the soil while satellite spectral observations only provide near surface concentrations of CO2. In July 2014, NASA successfully launched OCO-2 which provides 3km surface measurements of CO2 over land and oceans. We have collected nearly one year of Level 2 XCO2 data from the OCO-2 satellite for 3 sites of ~200 km2 at equatorial, temperate and high latitudes. Each selected site was part of the Fluxnet or ARM system with tower stations for measuring and collecting CO2 fluxes on an hourly basis, in addition to eddy transports of the other parameters. We are also planning to acquire the 4km NDVI products from MODIS and registering the data to the 3km XCO2 footprints for the three sites. We have implemented a restricted Boltzman machine on the quantum annealing D-Wave computer, a novel deep learning neural net, to be used for training with station data to infer CO2 fluxes from collocated XCO2, MODIS vegetative land cover and MERRA reanalysis surface exchange products. We will present performance assessments of the D-Wave Boltzman machine for generating XCO2 fluxes from the OCO-2 satellite observations for the 3 sites by

Fuzzy-neural network in the automatic detection and volumetry of the spleen on spiral CT scans

International Nuclear Information System (INIS)

Heitmann, K.R.; Mainz Univ.; Rueckert, S.; Heussel, C.P.; Thelen, M.; Kauczor, H.U.; Uthmann, T.

2000-01-01

Purpose: To assess spleen segmentation and volumetry in spiral CT scans with and without pathological changes of splenic tissue. Methods: The image analysis software HYBRIKON is based on region growing, self-organized neural nets, and fuzzy-anatomic rules. The neural nets were trained with spiral CT data from 10 patients, not used in the following evaluation on spiral CT scans from 19 patients. An experienced radiologist verified the results. The true positive and false positive areas were compared in terms to the areas marked by the radiologist. The results were compared with a standard thresholding method. Results: The neural nets achieved a higher accuracy than the thresholding method. Correlation coefficient of the fuzzy-neural nets: 0.99 (thresholding: 0.63). Mean true positive rate: 90% (thresholding: 75%), mean false positive rate: 5% (thresholding>100%). Pitfalls were caused by accessory spleens, extreme changes in the morphology (tumors, metastases, cysts), and parasplenic masses. Conclusions: Self-organizing neural nets combined with fuzzy rules are ready for use in the automatic detection and volumetry of the spleen in spiral CT scans. (orig.) [de

Bootstrapped neural nets versus regression kriging in the digital mapping of pedological attributes: the automatic and time-consuming perspectives

Science.gov (United States)

Langella, Giuliano; Basile, Angelo; Bonfante, Antonello; Manna, Piero; Terribile, Fabio

2013-04-01

Digital soil mapping procedures are widespread used to build two-dimensional continuous maps about several pedological attributes. Our work addressed a regression kriging (RK) technique and a bootstrapped artificial neural network approach in order to evaluate and compare (i) the accuracy of prediction, (ii) the susceptibility of being included in automatic engines (e.g. to constitute web processing services), and (iii) the time cost needed for calibrating models and for making predictions. Regression kriging is maybe the most widely used geostatistical technique in the digital soil mapping literature. Here we tried to apply the EBLUP regression kriging as it is deemed to be the most statistically sound RK flavor by pedometricians. An unusual multi-parametric and nonlinear machine learning approach was accomplished, called BAGAP (Bootstrap aggregating Artificial neural networks with Genetic Algorithms and Principal component regression). BAGAP combines a selected set of weighted neural nets having specified characteristics to yield an ensemble response. The purpose of applying these two particular models is to ascertain whether and how much a more cumbersome machine learning method could be much promising in making more accurate/precise predictions. Being aware of the difficulty to handle objects based on EBLUP-RK as well as BAGAP when they are embedded in environmental applications, we explore the susceptibility of them in being wrapped within Web Processing Services. Two further kinds of aspects are faced for an exhaustive evaluation and comparison: automaticity and time of calculation with/without high performance computing leverage.

The principles of artificial neural network information processing

International Nuclear Information System (INIS)

Dai, Ru-Wei

1993-01-01

In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as Perceptron, Back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally, the application of artificial neural network for Chinese Character Recognition is also given. (author)

The principles of artificial neural network information processing

International Nuclear Information System (INIS)

Dai, Ru-Wei

1993-01-01

In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as perception, back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally the application of artificial neural network for Chinese character recognition is also given. (author)

Neural nets for massively parallel optimization

Science.gov (United States)

Dixon, Laurence C. W.; Mills, David

1992-07-01

To apply massively parallel processing systems to the solution of large scale optimization problems it is desirable to be able to evaluate any function f(z), z (epsilon) Rn in a parallel manner. The theorem of Cybenko, Hecht Nielsen, Hornik, Stinchcombe and White, and Funahasi shows that this can be achieved by a neural network with one hidden layer. In this paper we address the problem of the number of nodes required in the layer to achieve a given accuracy in the function and gradient values at all points within a given n dimensional interval. The type of activation function needed to obtain nonsingular Hessian matrices is described and a strategy for obtaining accurate minimal networks presented.

LOGIC WITH EXCEPTION ON THE ALGEBRA OF FOURIER-DUAL OPERATIONS: NEURAL NET MECHANISM OF COGNITIVE DISSONANCE REDUCING

Directory of Open Access Journals (Sweden)

A. V. Pavlov

2014-01-01

Full Text Available A mechanism of cognitive dissonance reducing is demonstrated with approach for non-monotonic fuzzy-valued logics by Fourier-holography technique implementation developing. Cognitive dissonance occurs under perceiving of new information that contradicts to the existing subjective pattern of the outside world, represented by double Fourier-transform cascade with a hologram – neural layers interconnections matrix of inner information representation and logical conclusion. The hologram implements monotonic logic according to “General Modus Ponens” rule. New information is represented by a hologram of exclusion that implements interconnections of logical conclusion and exclusion for neural layers. The latter are linked by Fourier transform that determines duality of the algebra forming operations of conjunction and disjunction. Hologram of exclusion forms conclusion that is dual to the “General Modus Ponens” conclusion. It is shown, that trained for the main rule and exclusion system can be represented by two-layered neural network with separate interconnection matrixes for direct and inverse iterations. The network energy function is involved determining the cyclic dynamics character; dissipative factor causing convergence type of the dynamics is analyzed. Both “General Modus Ponens” and exclusion holograms recording conditions on the dynamics and convergence of the system are demonstrated. The system converges to a stable status, in which logical conclusion doesn’t depend on the inner information. Such kind of dynamics, leading to tolerance forming, is typical for ordinary kind of thinking, aimed at inner pattern of outside world stability. For scientific kind of thinking, aimed at adequacy of the inner pattern of the world, a mechanism is needed to stop the net relaxation; the mechanism has to be external relative to the model of logic. Computer simulation results for the learning conditions adequate to real holograms recording are

Control of 12-Cylinder Camless Engine with Neural Networks

OpenAIRE

Ashhab Moh’d Sami

2017-01-01

The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s). The inputs to the net are the intake valve lift (IVL) and intake valve closing timing (IVC) whereas the output of the net is the cylinder air charge (CAC). The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and appl...

Competition and Cooperation in Neural Nets : U.S.-Japan Joint Seminar

CERN Document Server

Arbib, Michael

1982-01-01

The human brain, wi th its hundred billion or more neurons, is both one of the most complex systems known to man and one of the most important. The last decade has seen an explosion of experimental research on the brain, but little theory of neural networks beyond the study of electrical properties of membranes and small neural circuits. Nonetheless, a number of workers in Japan, the United States and elsewhere have begun to contribute to a theory which provides techniques of mathematical analysis and computer simulation to explore properties of neural systems containing immense numbers of neurons. Recently, it has been gradually recognized that rather independent studies of the dynamics of pattern recognition, pattern format::ion, motor control, self-organization, etc. , in neural systems do in fact make use of common methods. We find that a "competition and cooperation" type of interaction plays a fundamental role in parallel information processing in the brain. The present volume brings together 23 papers ...

Modularity and Sparsity: Evolution of Neural Net Controllers in Physically Embodied Robots

Directory of Open Access Journals (Sweden)

Nicholas Livingston

2016-12-01

Full Text Available While modularity is thought to be central for the evolution of complexity and evolvability, it remains unclear how systems boot-strap themselves into modularity from random or fully integrated starting conditions. Clune et al. (2013 suggested that a positive correlation between sparsity and modularity is the prime cause of this transition. We sought to test the generality of this modularity-sparsity hypothesis by testing it for the first time in physically embodied robots. A population of ten Tadros — autonomous, surface-swimming robots propelled by a flapping tail — was used. Individuals varied only in the structure of their neural net control, a 2 x 6 x 2 network with recurrence in the hidden layer. Each of the 60 possible connections was coded in the genome, and could achieve one of three states: -1, 0, 1. Inputs were two light-dependent resistors and outputs were two motor control variables to the flapping tail, one for the frequency of the flapping and the other for the turning offset. Each Tadro was tested separately in a circular tank lit by a single overhead light source. Fitness was the amount of light gathered by a vertically oriented sensor that was disconnected from the controller net. Reproduction was asexual, with the top performer cloned and then all individuals entered into a roulette wheel selection process, with genomes mutated to create the offspring. The starting population of networks was randomly generated. Over ten generations, the population’s mean fitness increased two-fold. This evolution occurred in spite of an unintentional integer overflow problem in recurrent nodes in the hidden layer that caused outputs to oscillate. Our investigation of the oscillatory behavior showed that the mutual information of inputs and outputs was sufficient for the reactive behaviors observed. While we had predicted that both modularity and sparsity would follow the same trend as fitness, neither did so. Instead, selection gradients

NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

Science.gov (United States)

Chirayath, Ved

2018-01-01

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with

Results from a MA16-based neural trigger in an experiment looking for beauty

International Nuclear Information System (INIS)

Baldanza, C.; Beichter, J.; Bisi, F.; Bruels, N.; Bruschini, C.; Cotta-Ramusino, A.; D'Antone, I.; Malferrari, L.; Mazzanti, P.; Musico, P.; Novelli, P.; Odorici, F.; Odorico, R.; Passaseo, M.; Zuffa, M.

1996-01-01

Results from a neural-network trigger based on the digital MA16 chip of Siemens are reported. The neural trigger has been applied to data from the WA92 experiment, looking for beauty particles, which have been collected during a run in which a neural trigger module based on Intel's analog neural chip ETANN operated, as already reported. The MA16 board hosting the chip has a 16-bit I/O precision and a 53-bit precision for internal calculations. It operated at 50 MHz, yielding a response time for a 16 input-variable net of 3 μs for a Fisher discriminant (1-layer net) and of 6 μs for a 2-layer net. Results are compared with those previously obtained with the ETANN trigger. (orig.)

Results from a MA16-based neural trigger in an experiment looking for beauty

Energy Technology Data Exchange (ETDEWEB)

Baldanza, C. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Beichter, J. [Siemens AG, ZFE T ME2, 81730 Munich (Germany); Bisi, F. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Bruels, N. [Siemens AG, ZFE T ME2, 81730 Munich (Germany); Bruschini, C. [INFN/Genoa, Via Dodecaneso 33, 16146 Genoa (Italy); Cotta-Ramusino, A. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); D`Antone, I. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Malferrari, L. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Mazzanti, P. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Musico, P. [INFN/Genoa, Via Dodecaneso 33, 16146 Genoa (Italy); Novelli, P. [INFN/Genoa, Via Dodecaneso 33, 16146 Genoa (Italy); Odorici, F. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Odorico, R. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy); Passaseo, M. [CERN, 1211 Geneva 23 (Switzerland); Zuffa, M. [Istituto Nazionale di Fisica Nucleare, Bologna (Italy)

1996-07-11

Results from a neural-network trigger based on the digital MA16 chip of Siemens are reported. The neural trigger has been applied to data from the WA92 experiment, looking for beauty particles, which have been collected during a run in which a neural trigger module based on Intel`s analog neural chip ETANN operated, as already reported. The MA16 board hosting the chip has a 16-bit I/O precision and a 53-bit precision for internal calculations. It operated at 50 MHz, yielding a response time for a 16 input-variable net of 3 {mu}s for a Fisher discriminant (1-layer net) and of 6 {mu}s for a 2-layer net. Results are compared with those previously obtained with the ETANN trigger. (orig.).

Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches.

Science.gov (United States)

Crichton, Gamal; Guo, Yufan; Pyysalo, Sampo; Korhonen, Anna

2018-05-21

Link prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (∼ 6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics. In random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (∼ 15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (∼ 0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them. Our results indicate

ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation

OpenAIRE

Visin, Francesco; Ciccone, Marco; Romero, Adriana; Kastner, Kyle; Cho, Kyunghyun; Bengio, Yoshua; Matteucci, Matteo; Courville, Aaron

2015-01-01

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally ...

Streaming Parallel GPU Acceleration of Large-Scale filter-based Spiking Neural Networks

NARCIS (Netherlands)

L.P. Slazynski (Leszek); S.M. Bohte (Sander)

2012-01-01

htmlabstractThe arrival of graphics processing (GPU) cards suitable for massively parallel computing promises a↵ordable large-scale neural network simulation previously only available at supercomputing facil- ities. While the raw numbers suggest that GPUs may outperform CPUs by at least an order of

IMNN: Information Maximizing Neural Networks

Science.gov (United States)

Charnock, Tom; Lavaux, Guilhem; Wandelt, Benjamin D.

2018-04-01

This software trains artificial neural networks to find non-linear functionals of data that maximize Fisher information: information maximizing neural networks (IMNNs). As compressing large data sets vastly simplifies both frequentist and Bayesian inference, important information may be inadvertently missed. Likelihood-free inference based on automatically derived IMNN summaries produces summaries that are good approximations to sufficient statistics. IMNNs are robustly capable of automatically finding optimal, non-linear summaries of the data even in cases where linear compression fails: inferring the variance of Gaussian signal in the presence of noise, inferring cosmological parameters from mock simulations of the Lyman-α forest in quasar spectra, and inferring frequency-domain parameters from LISA-like detections of gravitational waveforms. In this final case, the IMNN summary outperforms linear data compression by avoiding the introduction of spurious likelihood maxima.

TasselNet: counting maize tassels in the wild via local counts regression network.

Science.gov (United States)

Lu, Hao; Cao, Zhiguo; Xiao, Yang; Zhuang, Bohan; Shen, Chunhua

2017-01-01

Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations. This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel Maize Tassels Counting ( MTC ) dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed TasselNet is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large margins and achieves the overall best counting

TasselNet: counting maize tassels in the wild via local counts regression network

Directory of Open Access Journals (Sweden)

Hao Lu

2017-11-01

Full Text Available Abstract Background Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations. Results This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel Maize Tassels Counting (MTC dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed TasselNet is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large

Pattern recognition neural-net by spatial mapping of biology visual field

Science.gov (United States)

Lin, Xin; Mori, Masahiko

2000-05-01

The method of spatial mapping in biology vision field is applied to artificial neural networks for pattern recognition. By the coordinate transform that is called the complex-logarithm mapping and Fourier transform, the input images are transformed into scale- rotation- and shift- invariant patterns, and then fed into a multilayer neural network for learning and recognition. The results of computer simulation and an optical experimental system are described.

Bach in 2014: Music Composition with Recurrent Neural Network

OpenAIRE

Liu, I-Ting; Ramakrishnan, Bhiksha

2014-01-01

We propose a framework for computer music composition that uses resilient propagation (RProp) and long short term memory (LSTM) recurrent neural network. In this paper, we show that LSTM network learns the structure and characteristics of music pieces properly by demonstrating its ability to recreate music. We also show that predicting existing music using RProp outperforms Back propagation through time (BPTT).

A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems.

Science.gov (United States)

Zhao, Haiquan; Zeng, Xiangping; Zhang, Jiashu; Liu, Yangguang; Wang, Xiaomin; Li, Tianrui

2011-01-01

To eliminate nonlinear channel distortion in chaotic communication systems, a novel joint-processing adaptive nonlinear equalizer based on a pipelined recurrent neural network (JPRNN) is proposed, using a modified real-time recurrent learning (RTRL) algorithm. Furthermore, an adaptive amplitude RTRL algorithm is adopted to overcome the deteriorating effect introduced by the nesting process. Computer simulations illustrate that the proposed equalizer outperforms the pipelined recurrent neural network (PRNN) and recurrent neural network (RNN) equalizers. Copyright © 2010 Elsevier Ltd. All rights reserved.

Neural signal processing for identifying failed fuel rods in nuclear reactors

International Nuclear Information System (INIS)

Seixas, Jose M. de; Soares Filho, William; Pereira, Wagner C.A.; Teles, Claudio C.B.

2002-01-01

Ultrasonic pulses were used for automatic detection of failed nuclear fuel rods. For experimental tests of the proposed method, an assembly prototype of 16 x 16 rods was built by using genuine rods but without fuel inside (just air). Some rods were partially filled with water to simulate cracked rods. Using neural signal processing on the received echoes of the emitted ultrasonic pulses, a detection efficiency of 97% was obtained. Neural detection is shown to outperform other classical discriminating methods and can also reveal important features of the signal structure of the received echoes. (author)

Data Compression of Seismic Images by Neural Networks Compression d'images sismiques par des réseaux neuronaux

Directory of Open Access Journals (Sweden)

Epping W. J. M.

2006-11-01

Full Text Available Neural networks with the multi-layered perceptron architecture were trained on an autoassociation task to compress 2D seismic data. Networks with linear transfer functions outperformed nonlinear neural nets with single or multiple hidden layers. This indicates that the correlational structure of the seismic data is predominantly linear. A compression factor of 5 to 7 can be achieved if a reconstruction error of 10% is allowed. The performance on new test data was similar to that achieved with the training data. The hidden units developed feature-detecting properties that resemble oriented line, edge and more complex feature detectors. The feature detectors of linear neural nets are near-orthogonal rotations of the principal eigenvectors of the Karhunen-Loève transformation. Des réseaux neuronaux à architecture de perceptron multicouches ont été expérimentés en auto-association pour permettre la compression de données sismiques bidimensionnelles. Les réseaux neuronaux à fonctions de transfert linéaires s'avèrent plus performants que les réseaux neuronaux non linéaires, à une ou plusieurs couches cachées. Ceci indique que la structure corrélative des données sismiques est à prédominance linéaire. Un facteur de compression de 5 à 7 peut être obtenu si une erreur de reconstruction de 10 % est admise. La performance sur les données de test est très proche de celle obtenue sur les données d'apprentissage. Les unités cachées développent des propriétés de détection de caractéristiques ressemblant à des détecteurs de lignes orientées, de bords et de figures plus complexes. Les détecteurs de caractéristique des réseaux neuronaux linéaires sont des rotations quasi orthogonales des vecteurs propres principaux de la transformation de Karhunen-Loève.

Predicting local field potentials with recurrent neural networks.

Science.gov (United States)

Kim, Louis; Harer, Jacob; Rangamani, Akshay; Moran, James; Parks, Philip D; Widge, Alik; Eskandar, Emad; Dougherty, Darin; Chin, Sang Peter

2016-08-01

We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.

A neutron spectrum unfolding computer code based on artificial neural networks

International Nuclear Information System (INIS)

Ortiz-Rodríguez, J.M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J.M.; Vega-Carrillo, H.R.

2014-01-01

The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6 LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding

Neural network error correction for solving coupled ordinary differential equations

Science.gov (United States)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

Application of a neural network for reflectance spectrum classification

Science.gov (United States)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

Evaluation and scoring of radiotherapy treatment plans using an artificial neural network

International Nuclear Information System (INIS)

Willoughby, Twyla R.; Starkschall, George; Janjan, Nora A.; Rosen, Isaac I.

1996-01-01

Purpose: The objective of this work was to demonstrate the feasibility of using an artificial neural network to predict the clinical evaluation of radiotherapy treatment plans. Methods and Materials: Approximately 150 treatment plans were developed for 16 patients who received external-beam radiotherapy for soft-tissue sarcomas of the lower extremity. Plans were assigned a figure of merit by a radiation oncologist using a five-point rating scale. Plan scoring was performed by a single physician to ensure consistency in rating. Dose-volume information extracted from a training set of 511 treatment plans on 14 patients was correlated to the physician-generated figure of merit using an artificial neural network. The neural network was tested with a test set of 19 treatment plans on two patients whose plans were not used in the training of the neural net. Results: Physician scoring of treatment plans was consistent to within one point on the rating scale 88% of the time. The neural net reproduced the physician scores in the training set to within one point approximately 90% of the time. It reproduced the physician scores in the test set to within one point approximately 83% of the time. Conclusions: An artificial neural network can be trained to generate a score for a treatment plan that can be correlated to a clinically-based figure of merit. The accuracy of the neural net in scoring plans compares well with the reproducibility of the clinical scoring. The system of radiotherapy treatment plan evaluation using an artificial neural network demonstrates promise as a method for generating a clinically relevant figure of merit

Neural nets for the plausibility check of measured values in the integrated measurement and information system for the surveillance of environmental radioactivity (IMIS)

International Nuclear Information System (INIS)

Haase, G.

2003-01-01

Neural nets to the plausibility check of measured values in the ''integrated measurement and information system for the surveillance of environmental radioactivity, IMIS'' is a research project supported by the Federal Minister for the Environment, Nature Conservation and Nuclear Safety. A goal of this project was the automatic recognition of implausible measured values in the data base ORACLE, which measured values from surveillance of environmental radioactivity of most diverse environmental media contained. The conversion of this project [ 1 ] was realized by institut of logic, complexity and deduction systems of the university Karlsruhe under the direction of Professor Dr. Menzel, Dr. Martin Riedmueller and Martin Lauer. (orig.)

Reconstruction of neutron spectra through neural networks; Reconstruccion de espectros de neutrones mediante redes neuronales

Energy Technology Data Exchange (ETDEWEB)

Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E. [Cuerpo Academico de Radiobiologia, Estudios Nucleares, Universidad Autonoma de Zacatecas, A.P. 336, 98000 Zacatecas (Mexico)] e-mail: rvega@cantera.reduaz.mx [and others

2003-07-01

A neural network has been used to reconstruct the neutron spectra starting from the counting rates of the detectors of the Bonner sphere spectrophotometric system. A group of 56 neutron spectra was selected to calculate the counting rates that would produce in a Bonner sphere system, with these data and the spectra it was trained the neural network. To prove the performance of the net, 12 spectra were used, 6 were taken of the group used for the training, 3 were obtained of mathematical functions and those other 3 correspond to real spectra. When comparing the original spectra of those reconstructed by the net we find that our net has a poor performance when reconstructing monoenergetic spectra, this attributes it to those characteristic of the spectra used for the training of the neural network, however for the other groups of spectra the results of the net are appropriate with the prospective ones. (Author)

Convolutional neural network approach for enhanced capture of breast parenchymal complexity patterns associated with breast cancer risk

Science.gov (United States)

Oustimov, Andrew; Gastounioti, Aimilia; Hsieh, Meng-Kang; Pantalone, Lauren; Conant, Emily F.; Kontos, Despina

2017-03-01

We assess the feasibility of a parenchymal texture feature fusion approach, utilizing a convolutional neural network (ConvNet) architecture, to benefit breast cancer risk assessment. Hypothesizing that by capturing sparse, subtle interactions between localized motifs present in two-dimensional texture feature maps derived from mammographic images, a multitude of texture feature descriptors can be optimally reduced to five meta-features capable of serving as a basis on which a linear classifier, such as logistic regression, can efficiently assess breast cancer risk. We combine this methodology with our previously validated lattice-based strategy for parenchymal texture analysis and we evaluate the feasibility of this approach in a case-control study with 424 digital mammograms. In a randomized split-sample setting, we optimize our framework in training/validation sets (N=300) and evaluate its descriminatory performance in an independent test set (N=124). The discriminatory capacity is assessed in terms of the the area under the curve (AUC) of the receiver operator characteristic (ROC). The resulting meta-features exhibited strong classification capability in the test dataset (AUC = 0.90), outperforming conventional, non-fused, texture analysis which previously resulted in an AUC=0.85 on the same case-control dataset. Our results suggest that informative interactions between localized motifs exist and can be extracted and summarized via a fairly simple ConvNet architecture.

Generalized Net Model of the Cognitive and Neural Algorithm for Adaptive Resonance Theory 1

Directory of Open Access Journals (Sweden)

Todor Petkov

2013-12-01

Full Text Available The artificial neural networks are inspired by biological properties of human and animal brains. One of the neural networks type is called ART [4]. The abbreviation of ART stands for Adaptive Resonance Theory that has been invented by Stephen Grossberg in 1976 [5]. ART represents a family of Neural Networks. It is a cognitive and neural theory that describes how the brain autonomously learns to categorize, recognize and predict objects and events in the changing world. In this paper we introduce a GN model that represent ART1 Neural Network learning algorithm [1]. The purpose of this model is to explain when the input vector will be clustered or rejected among all nodes by the network. It can also be used for explanation and optimization of ART1 learning algorithm.

Application of artificial neural nets to Shashlik calorimetry

International Nuclear Information System (INIS)

Bonesini, M.; Paganoni, M.; Terranova, F.

1997-01-01

Artificial neural networks (ANN) are powerful tools widely used in high-energy physics to solve track finding and particle identification problems. An entirely new class of application is related to the problem of recovering the information lost during data taking or signal transmission. Good performances can be reached by ANN when the events are described by quite regular patterns. Such a method was used for the DELPHI luminosity monitor (STIC) to recover calorimeter dead channels. A comparison with more traditional techniques is also given. (orig.)

Analysis of Salinity Intrusion in the San Francisco Bay-Delta Using a GA-Optimized Neural Net, and Application of the Model to Prediction in the Elkhorn Slough Habitat

Science.gov (United States)

Thompson, D. E.; Rajkumar, T.

2002-12-01

The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Suisan Marsh, and the San Francisco Bay proper. Competition exists for the use of this extensive water system both from the fisheries industry, the agricultural industry, and from the marine and estuarine animal species within the Delta. As tidal fluctuations occur, more saline water pushes upstream allowing fish to migrate beyond the Suisan Marsh for breeding and habitat occupation. However, the agriculture industry does not want extensive salinity intrusion to impact water quality for human and plant consumption. The balance is regulated by pumping stations located along the estuaries and reservoirs whereby flushing of fresh water keeps the saline intrusion at bay. The pumping schedule is driven by data collected at various locations within the Bay Delta and by numerical models that predict the salinity intrusion as part of a larger model of the system. The Interagency Ecological Program (IEP) for the San Francisco Bay / Sacramento-San Joaquin Estuary collects, monitors, and archives the data, and the Department of Water Resources provides a numerical model simulation (DSM2) from which predictions are made that drive the pumping schedule. A problem with DSM2 is that the numerical simulation takes roughly 16 hours to complete a prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple gauging stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Suisan Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the Bay-Delta is strongly tidally driven, we used both Principal Component Analysis and Fast Fourier Transforms to discover dominant features within the IEP data. We then filtered out the dominant tidal forcing to discover non-primary tidal effects

NeMO-Net - The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

Science.gov (United States)

Li, A. S. X.; Chirayath, V.; Segal-Rosenhaimer, M.; Das, K.

2017-12-01

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8% error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets.We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Python's extensive libraries for machine learning, as well as extending integration to GPU

Prediction of Clinical Deterioration in Hospitalized Adult Patients with Hematologic Malignancies Using a Neural Network Model.

Directory of Open Access Journals (Sweden)

Scott B Hu

Full Text Available Clinical deterioration (ICU transfer and cardiac arrest occurs during approximately 5-10% of hospital admissions. Existing prediction models have a high false positive rate, leading to multiple false alarms and alarm fatigue. We used routine vital signs and laboratory values obtained from the electronic medical record (EMR along with a machine learning algorithm called a neural network to develop a prediction model that would increase the predictive accuracy and decrease false alarm rates.Retrospective cohort study.The hematologic malignancy unit in an academic medical center in the United States.Adult patients admitted to the hematologic malignancy unit from 2009 to 2010.None.Vital signs and laboratory values were obtained from the electronic medical record system and then used as predictors (features. A neural network was used to build a model to predict clinical deterioration events (ICU transfer and cardiac arrest. The performance of the neural network model was compared to the VitalPac Early Warning Score (ViEWS. Five hundred sixty five consecutive total admissions were available with 43 admissions resulting in clinical deterioration. Using simulation, the neural network outperformed the ViEWS model with a positive predictive value of 82% compared to 24%, respectively.We developed and tested a neural network-based prediction model for clinical deterioration in patients hospitalized in the hematologic malignancy unit. Our neural network model outperformed an existing model, substantially increasing the positive predictive value, allowing the clinician to be confident in the alarm raised. This system can be readily implemented in a real-time fashion in existing EMR systems.

Neural net classification of x-ray pistachio nut data

Science.gov (United States)

Casasent, David P.; Sipe, Michael A.; Schatzki, Thomas F.; Keagy, Pamela M.; Le, Lan Chau

1996-12-01

Classification results for agricultural products are presented using a new neural network. This neural network inherently produces higher-order decision surfaces. It achieves this with fewer hidden layer neurons than other classifiers require. This gives better generalization. It uses new techniques to select the number of hidden layer neurons and adaptive algorithms that avoid other such ad hoc parameter selection problems; it allows selection of the best classifier parameters without the need to analyze the test set results. The agriculture case study considered is the inspection and classification of pistachio nuts using x- ray imagery. Present inspection techniques cannot provide good rejection of worm damaged nuts without rejecting too many good nuts. X-ray imagery has the potential to provide 100% inspection of such agricultural products in real time. Only preliminary results are presented, but these indicate the potential to reduce major defects to 2% of the crop with 1% of good nuts rejected. Future image processing techniques that should provide better features to improve performance and allow inspection of a larger variety of nuts are noted. These techniques and variations of them have uses in a number of other agricultural product inspection problems.

Fuzzy Neuroidal Nets and Recurrent Fuzzy Computations

Czech Academy of Sciences Publication Activity Database

Wiedermann, Jiří

2001-01-01

Roč. 11, č. 6 (2001), s. 675-686 ISSN 1210-0552. [SOFSEM 2001 Workshop on Soft Computing. Piešťany, 29.11.2001-30.11.2001] R&D Projects: GA ČR GA201/00/1489; GA AV ČR KSK1019101 Institutional research plan: AV0Z1030915 Keywords : fuzzy computing * fuzzy neural nets * fuzzy Turing machines * non-uniform computational complexity Subject RIV: BA - General Mathematics

Segmentation of corneal endothelium images using a U-Net-based convolutional neural network.

Science.gov (United States)

Fabijańska, Anna

2018-04-18

Diagnostic information regarding the health status of the corneal endothelium may be obtained by analyzing the size and the shape of the endothelial cells in specular microscopy images. Prior to the analysis, the endothelial cells need to be extracted from the image. Up to today, this has been performed manually or semi-automatically. Several approaches to automatic segmentation of endothelial cells exist; however, none of them is perfect. Therefore this paper proposes to perform cell segmentation using a U-Net-based convolutional neural network. Particularly, the network is trained to discriminate pixels located at the borders between cells. The edge probability map outputted by the network is next binarized and skeletonized in order to obtain one-pixel wide edges. The proposed solution was tested on a dataset consisting of 30 corneal endothelial images presenting cells of different sizes, achieving an AUROC level of 0.92. The resulting DICE is on average equal to 0.86, which is a good result, regarding the thickness of the compared edges. The corresponding mean absolute percentage error of cell number is at the level of 4.5% which confirms the high accuracy of the proposed approach. The resulting cell edges are well aligned to the ground truths and require a limited number of manual corrections. This also results in accurate values of the cell morphometric parameters. The corresponding errors range from 5.2% for endothelial cell density, through 6.2% for cell hexagonality to 11.93% for the coefficient of variation of the cell size. Copyright © 2018 Elsevier B.V. All rights reserved.

State-of-the-art of applications of neural networks in the nuclear industry

International Nuclear Information System (INIS)

Zwingelstein, G.; Masson, M.H.

1990-01-01

Artificial neural net models have been extensively studied for many years in various laboratories to try to simulate with computer programs the human brain performances. The first applications were developed in the fields of speech and image recognition. The aims of these studies were mainly to classify rapidly patterns corrupted by noises or partly missing. Neural networks with the development of new net topologies and algorithms and parallel computing hardwares and softwares are to-day very promising for applications in many industries. In the introduction, this paper presents the anticipated benefits of the uses of neural networks for industrial applications. Then a brief overview of the main neural networks is provided. Finally a short review of neural networks applications in the nuclear industry is given. It covers domains such as: predictive maintenance for vibratory surveillance of rotating machinery, signal processing, operator guidance and eddy current inspection. In conclusion recommendations are made to use with efficiency neural networks for practical applications. In particular the need for supercomputing will be pinpointed. (author)

Global reinforcement training of CrossNets

Science.gov (United States)

Ma, Xiaolong

2007-10-01

Hybrid "CMOL" integrated circuits, incorporating advanced CMOS devices for neural cell bodies, nanowires as axons and dendrites, and latching switches as synapses, may be used for the hardware implementation of extremely dense (107 cells and 1012 synapses per cm2) neuromorphic networks, operating up to 10 6 times faster than their biological prototypes. We are exploring several "Cross- Net" architectures that accommodate the limitations imposed by CMOL hardware and should allow effective training of the networks without a direct external access to individual synapses. Our studies have show that CrossNets based on simple (two-terminal) crosspoint devices can work well in at least two modes: as Hop-field networks for associative memory and multilayer perceptrons for classification tasks. For more intelligent tasks (such as robot motion control or complex games), which do not have "examples" for supervised learning, more advanced training methods such as the global reinforcement learning are necessary. For application of global reinforcement training algorithms to CrossNets, we have extended Williams's REINFORCE learning principle to a more general framework and derived several learning rules that are more suitable for CrossNet hardware implementation. The results of numerical experiments have shown that these new learning rules can work well for both classification tasks and reinforcement tasks such as the cartpole balancing control problem. Some limitations imposed by the CMOL hardware need to be carefully addressed for the the successful application of in situ reinforcement training to CrossNets.

Using neural networks and extreme value distributions to model electricity pool prices: Evidence from the Australian National Electricity Market 1998–2013

International Nuclear Information System (INIS)

Dev, Priya; Martin, Michael A.

2014-01-01

Highlights: • Neural nets are unable to properly capture spiky price behavior found in the electricity market. • We modeled electricity price data from the Australian National Electricity Market over 15 years. • Neural nets need to be augmented with other modeling techniques to capture price spikes. • We fit a Generalized Pareto Distribution to price spikes using a peaks-over-thresholds approach. - Abstract: Competitors in the electricity supply industry desire accurate predictions of electricity spot prices to hedge against financial risks. Neural networks are commonly used for forecasting such prices, but certain features of spot price series, such as extreme price spikes, present critical challenges for such modeling. We investigate the predictive capacity of neural networks for electricity spot prices using Australian National Electricity Market data. Following neural net modeling of the data, we explore extreme price spikes through extreme value modeling, fitting a Generalized Pareto Distribution to price peaks over an estimated threshold. While neural nets capture the smoother aspects of spot price data, they are unable to capture local, volatile features that characterize electricity spot price data. Price spikes can be modeled successfully through extreme value modeling

Portable Rule Extraction Method for Neural Network Decisions Reasoning

Directory of Open Access Journals (Sweden)

Darius PLIKYNAS

2005-08-01

Full Text Available Neural network (NN methods are sometimes useless in practical applications, because they are not properly tailored to the particular market's needs. We focus thereinafter specifically on financial market applications. NNs have not gained full acceptance here yet. One of the main reasons is the "Black Box" problem (lack of the NN decisions explanatory power. There are though some NN decisions rule extraction methods like decompositional, pedagogical or eclectic, but they suffer from low portability of the rule extraction technique across various neural net architectures, high level of granularity, algorithmic sophistication of the rule extraction technique etc. The authors propose to eliminate some known drawbacks using an innovative extension of the pedagogical approach. The idea is exposed by the use of a widespread MLP neural net (as a common tool in the financial problems' domain and SOM (input data space clusterization. The feedback of both nets' performance is related and targeted through the iteration cycle by achievement of the best matching between the decision space fragments and input data space clusters. Three sets of rules are generated algorithmically or by fuzzy membership functions. Empirical validation of the common financial benchmark problems is conducted with an appropriately prepared software solution.

Neural Network Approach to Locating Cryptography in Object Code

Energy Technology Data Exchange (ETDEWEB)

Jason L. Wright; Milos Manic

2009-09-01

Finding and identifying cryptography is a growing concern in the malware analysis community. In this paper, artificial neural networks are used to classify functional blocks from a disassembled program as being either cryptography related or not. The resulting system, referred to as NNLC (Neural Net for Locating Cryptography) is presented and results of applying this system to various libraries are described.

Weak-value measurements can outperform conventional measurements

International Nuclear Information System (INIS)

Magaña-Loaiza, Omar S; Boyd, Robert W; Harris, Jérémie; Lundeen, Jeff S

2017-01-01

In this paper we provide a simple, straightforward example of a specific situation in which weak-value amplification (WVA) clearly outperforms conventional measurement in determining the angular orientation of an optical component. We also offer a perspective reconciling the views of some theorists, who claim WVA to be inherently sub-optimal for parameter estimation, with the perspective of the many experimentalists and theorists who have used the procedure to successfully access otherwise elusive phenomena. (invited comment)

Stimulus-dependent maximum entropy models of neural population codes.

Directory of Open Access Journals (Sweden)

Einat Granot-Atedgi

Full Text Available Neural populations encode information about their stimulus in a collective fashion, by joint activity patterns of spiking and silence. A full account of this mapping from stimulus to neural activity is given by the conditional probability distribution over neural codewords given the sensory input. For large populations, direct sampling of these distributions is impossible, and so we must rely on constructing appropriate models. We show here that in a population of 100 retinal ganglion cells in the salamander retina responding to temporal white-noise stimuli, dependencies between cells play an important encoding role. We introduce the stimulus-dependent maximum entropy (SDME model-a minimal extension of the canonical linear-nonlinear model of a single neuron, to a pairwise-coupled neural population. We find that the SDME model gives a more accurate account of single cell responses and in particular significantly outperforms uncoupled models in reproducing the distributions of population codewords emitted in response to a stimulus. We show how the SDME model, in conjunction with static maximum entropy models of population vocabulary, can be used to estimate information-theoretic quantities like average surprise and information transmission in a neural population.

Invariant 2D object recognition using the wavelet transform and structured neural networks

Science.gov (United States)

Khalil, Mahmoud I.; Bayoumi, Mohamed M.

1999-03-01

This paper applies the dyadic wavelet transform and the structured neural networks approach to recognize 2D objects under translation, rotation, and scale transformation. Experimental results are presented and compared with traditional methods. The experimental results showed that this refined technique successfully classified the objects and outperformed some traditional methods especially in the presence of noise.

Markers of neural degeneration and regeneration in Down ...

African Journals Online (AJOL)

Iman Ehsan Abdel-Meguid

2012-11-02

Nov 2, 2012 ... The Egyptian Journal of Medical Human Genetics www.ejmhg.eg.net ... stem cells (TCSCs), including neural TCSCs and endothelial. TCSCs [10,11]. ..... directs human embryonic stem cell proliferation and differentia- tion into.

Do bilinguals outperform monolinguals?

Directory of Open Access Journals (Sweden)

Sejdi Sejdiu

2016-11-01

Full Text Available The relationship between second dialect acquisition and the psychological capacity of the learner is still a divisive topic that generates a lot of debate. A few researchers contend that the acquisition of the second dialect tends to improve the cognitive abilities in various individuals, but at the same time it could hinder the same abilities in other people. Currently, immersion is a common occurrence in some countries. In the recent past, it has significantly increased in its popularity, which has caused parents, professionals, and researchers to question whether second language acquisition has a positive impact on cognitive development, encompassing psychological ability. In rundown, the above might decide to comprehend the effects of using a second language based on the literal aptitudes connected with the native language. The issue of bilingualism was seen as a disadvantage until recently because of two languages being present which would hinder or delay the development of languages. However, recent studies have proven that bilinguals outperform monolinguals in tasks which require more attention.

Neural networks and applications tutorial

Science.gov (United States)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

End-to-end unsupervised deformable image registration with a convolutional neural network

NARCIS (Netherlands)

de Vos, Bob D.; Berendsen, Floris; Viergever, Max A.; Staring, Marius; Išgum, Ivana

2017-01-01

In this work we propose a deep learning network for deformable image registration (DIRNet). The DIRNet consists of a convolutional neural network (ConvNet) regressor, a spatial transformer, and a resampler. The ConvNet analyzes a pair of fixed and moving images and outputs parameters for the spatial

Optical neural network system for pose determination of spinning satellites

Science.gov (United States)

Lee, Andrew; Casasent, David

1990-01-01

An optical neural network architecture and algorithm based on a Hopfield optimization network are presented for multitarget tracking. This tracker utilizes a neuron for every possible target track, and a quadratic energy function of neural activities which is minimized using gradient descent neural evolution. The neural net tracker is demonstrated as part of a system for determining position and orientation (pose) of spinning satellites with respect to a robotic spacecraft. The input to the system is time sequence video from a single camera. Novelty detection and filtering are utilized to locate and segment novel regions from the input images. The neural net multitarget tracker determines the correspondences (or tracks) of the novel regions as a function of time, and hence the paths of object (satellite) parts. The path traced out by a given part or region is approximately elliptical in image space, and the position, shape and orientation of the ellipse are functions of the satellite geometry and its pose. Having a geometric model of the satellite, and the elliptical path of a part in image space, the three-dimensional pose of the satellite is determined. Digital simulation results using this algorithm are presented for various satellite poses and lighting conditions.

Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees

International Nuclear Information System (INIS)

Jerebko, Anna K.; Summers, Ronald M.; Malley, James D.; Franaszek, Marek; Johnson, C. Daniel

2003-01-01

Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study

Processing of chromatic information in a deep convolutional neural network.

Science.gov (United States)

Flachot, Alban; Gegenfurtner, Karl R

2018-04-01

Deep convolutional neural networks are a class of machine-learning algorithms capable of solving non-trivial tasks, such as object recognition, with human-like performance. Little is known about the exact computations that deep neural networks learn, and to what extent these computations are similar to the ones performed by the primate brain. Here, we investigate how color information is processed in the different layers of the AlexNet deep neural network, originally trained on object classification of over 1.2M images of objects in their natural contexts. We found that the color-responsive units in the first layer of AlexNet learned linear features and were broadly tuned to two directions in color space, analogously to what is known of color responsive cells in the primate thalamus. Moreover, these directions are decorrelated and lead to statistically efficient representations, similar to the cardinal directions of the second-stage color mechanisms in primates. We also found, in analogy to the early stages of the primate visual system, that chromatic and achromatic information were segregated in the early layers of the network. Units in the higher layers of AlexNet exhibit on average a lower responsivity for color than units at earlier stages.

Computation and control with neural nets

Energy Technology Data Exchange (ETDEWEB)

Corneliusen, A.; Terdal, P.; Knight, T.; Spencer, J.

1989-10-04

As energies have increased exponentially with time so have the size and complexity of accelerators and control systems. NN may offer the kinds of improvements in computation and control that are needed to maintain acceptable functionality. For control their associative characteristics could provide signal conversion or data translation. Because they can do any computation such as least squares, they can close feedback loops autonomously to provide intelligent control at the point of action rather than at a central location that requires transfers, conversions, hand-shaking and other costly repetitions like input protection. Both computation and control can be integrated on a single chip, printed circuit or an optical equivalent that is also inherently faster through full parallel operation. For such reasons one expects lower costs and better results. Such systems could be optimized by integrating sensor and signal processing functions. Distributed nets of such hardware could communicate and provide global monitoring and multiprocessing in various ways e.g. via token, slotted or parallel rings (or Steiner trees) for compatibility with existing systems. Problems and advantages of this approach such as an optimal, real-time Turing machine are discussed. Simple examples are simulated and hardware implemented using discrete elements that demonstrate some basic characteristics of learning and parallelism. Future microprocessors' are predicted and requested on this basis. 19 refs., 18 figs.

Computation and control with neural nets

International Nuclear Information System (INIS)

Corneliusen, A.; Terdal, P.; Knight, T.; Spencer, J.

1989-01-01

As energies have increased exponentially with time so have the size and complexity of accelerators and control systems. NN may offer the kinds of improvements in computation and control that are needed to maintain acceptable functionality. For control their associative characteristics could provide signal conversion or data translation. Because they can do any computation such as least squares, they can close feedback loops autonomously to provide intelligent control at the point of action rather than at a central location that requires transfers, conversions, hand-shaking and other costly repetitions like input protection. Both computation and control can be integrated on a single chip, printed circuit or an optical equivalent that is also inherently faster through full parallel operation. For such reasons one expects lower costs and better results. Such systems could be optimized by integrating sensor and signal processing functions. Distributed nets of such hardware could communicate and provide global monitoring and multiprocessing in various ways e.g. via token, slotted or parallel rings (or Steiner trees) for compatibility with existing systems. Problems and advantages of this approach such as an optimal, real-time Turing machine are discussed. Simple examples are simulated and hardware implemented using discrete elements that demonstrate some basic characteristics of learning and parallelism. Future 'microprocessors' are predicted and requested on this basis. 19 refs., 18 figs

Complementary Variety: When Can Cooperation in Uncertain Environments Outperform Competitive Selection?

Directory of Open Access Journals (Sweden)

Martin Hilbert

2017-01-01

Full Text Available Evolving biological and socioeconomic populations can sometimes increase their growth rate by cooperatively redistributing resources among their members. In unchanging environments, this simply comes down to reallocating resources to fitter types. In uncertain and fluctuating environments, cooperation cannot always outperform blind competitive selection. When can it? The conditions depend on the particular shape of the fitness landscape. The article derives a single measure that quantifies by how much an intervention in stochastic environments can possibly outperform the blind forces of natural selection. It is a multivariate and multilevel measure that essentially quantifies the amount of complementary variety between different population types and environmental states. The more complementary the fitness of types in different environmental states, the proportionally larger the potential benefit of strategic cooperation over competitive selection. With complementary variety, holding population shares constant will always outperform natural and market selection (including bet-hedging, portfolio management, and stochastic switching. The result can be used both to determine the acceptable cost of learning the details of a fitness landscape and to design multilevel classification systems of population types and environmental states that maximize population growth. Two empirical cases are explored, one from the evolving economy and the other one from migrating birds.

Forecasting macroeconomic variables using neural network models and three automated model selection techniques

DEFF Research Database (Denmark)

Kock, Anders Bredahl; Teräsvirta, Timo

2016-01-01

When forecasting with neural network models one faces several problems, all of which influence the accuracy of the forecasts. First, neural networks are often hard to estimate due to their highly nonlinear structure. To alleviate the problem, White (2006) presented a solution (QuickNet) that conv...

WATER DEMAND PREDICTION USING ARTIFICIAL NEURAL ...

African Journals Online (AJOL)

This paper presents Hourly water demand prediction at the demand nodes of a water distribution network using NeuNet Pro 2.3 neural network software and the monitoring and control of water distribution using supervisory control. The case study is the Laminga Water Treatment Plant and its water distribution network, Jos.

A Tensor-Product-Kernel Framework for Multiscale Neural Activity Decoding and Control

Science.gov (United States)

Li, Lin; Brockmeier, Austin J.; Choi, John S.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2014-01-01

Brain machine interfaces (BMIs) have attracted intense attention as a promising technology for directly interfacing computers or prostheses with the brain's motor and sensory areas, thereby bypassing the body. The availability of multiscale neural recordings including spike trains and local field potentials (LFPs) brings potential opportunities to enhance computational modeling by enriching the characterization of the neural system state. However, heterogeneity on data type (spike timing versus continuous amplitude signals) and spatiotemporal scale complicates the model integration of multiscale neural activity. In this paper, we propose a tensor-product-kernel-based framework to integrate the multiscale activity and exploit the complementary information available in multiscale neural activity. This provides a common mathematical framework for incorporating signals from different domains. The approach is applied to the problem of neural decoding and control. For neural decoding, the framework is able to identify the nonlinear functional relationship between the multiscale neural responses and the stimuli using general purpose kernel adaptive filtering. In a sensory stimulation experiment, the tensor-product-kernel decoder outperforms decoders that use only a single neural data type. In addition, an adaptive inverse controller for delivering electrical microstimulation patterns that utilizes the tensor-product kernel achieves promising results in emulating the responses to natural stimulation. PMID:24829569

Towards semen quality assessment using neural networks

DEFF Research Database (Denmark)

Linneberg, Christian; Salamon, P.; Svarer, C.

1994-01-01

The paper presents the methodology and results from a neural net based classification of human sperm head morphology. The methodology uses a preprocessing scheme in which invariant Fourier descriptors are lumped into “energy” bands. The resulting networks are pruned using optimal brain damage. Pe...

Quantitative phase microscopy using deep neural networks

Science.gov (United States)

Li, Shuai; Sinha, Ayan; Lee, Justin; Barbastathis, George

2018-02-01

Deep learning has been proven to achieve ground-breaking accuracy in various tasks. In this paper, we implemented a deep neural network (DNN) to achieve phase retrieval in a wide-field microscope. Our DNN utilized the residual neural network (ResNet) architecture and was trained using the data generated by a phase SLM. The results showed that our DNN was able to reconstruct the profile of the phase target qualitatively. In the meantime, large error still existed, which indicated that our approach still need to be improved.

A biologically inspired neural net for trajectory formation and obstacle avoidance.

Science.gov (United States)

Glasius, R; Komoda, A; Gielen, S C

1996-06-01

In this paper we present a biologically inspired two-layered neural network for trajectory formation and obstacle avoidance. The two topographically ordered neural maps consist of analog neurons having continuous dynamics. The first layer, the sensory map, receives sensory information and builds up an activity pattern which contains the optimal solution (i.e. shortest path without collisions) for any given set of current position, target positions and obstacle positions. Targets and obstacles are allowed to move, in which case the activity pattern in the sensory map will change accordingly. The time evolution of the neural activity in the second layer, the motor map, results in a moving cluster of activity, which can be interpreted as a population vector. Through the feedforward connections between the two layers, input of the sensory map directs the movement of the cluster along the optimal path from the current position of the cluster to the target position. The smooth trajectory is the result of the intrinsic dynamics of the network only. No supervisor is required. The output of the motor map can be used for direct control of an autonomous system in a cluttered environment or for control of the actuators of a biological limb or robot manipulator. The system is able to reach a target even in the presence of an external perturbation. Computer simulations of a point robot and a multi-joint manipulator illustrate the theory.

Control of 12-Cylinder Camless Engine with Neural Networks

Directory of Open Access Journals (Sweden)

Ashhab Moh’d Sami

2017-01-01

Full Text Available The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s. The inputs to the net are the intake valve lift (IVL and intake valve closing timing (IVC whereas the output of the net is the cylinder air charge (CAC. The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and applied to the camless engine ANN model. As a consequence the overall 12-cyliner camless engine feedback controller is upgraded and the necessary changes are implemented in order to contain the adaptive neural network with the objective of tracking the cylinder air charge (driver’s torque demand while minimizing the pumping losses (increasing engine efficiency. All the needed measurements are extracted only from the two conventional and inexpensive sensors, namely, the mass air flow through the throttle body (MAF and the intake manifold absolute pressure (MAP sensors. The feedback controller’s capability is demonstrated through computer simulation.

Approach to design neural cryptography: a generalized architecture and a heuristic rule.

Science.gov (United States)

Mu, Nankun; Liao, Xiaofeng; Huang, Tingwen

2013-06-01

Neural cryptography, a type of public key exchange protocol, is widely considered as an effective method for sharing a common secret key between two neural networks on public channels. How to design neural cryptography remains a great challenge. In this paper, in order to provide an approach to solve this challenge, a generalized network architecture and a significant heuristic rule are designed. The proposed generic framework is named as tree state classification machine (TSCM), which extends and unifies the existing structures, i.e., tree parity machine (TPM) and tree committee machine (TCM). Furthermore, we carefully study and find that the heuristic rule can improve the security of TSCM-based neural cryptography. Therefore, TSCM and the heuristic rule can guide us to designing a great deal of effective neural cryptography candidates, in which it is possible to achieve the more secure instances. Significantly, in the light of TSCM and the heuristic rule, we further expound that our designed neural cryptography outperforms TPM (the most secure model at present) on security. Finally, a series of numerical simulation experiments are provided to verify validity and applicability of our results.

MULTISPECTRAL PANSHARPENING APPROACH USING PULSE-COUPLED NEURAL NETWORK SEGMENTATION

Directory of Open Access Journals (Sweden)

X. J. Li

2018-04-01

Full Text Available The paper proposes a novel pansharpening method based on the pulse-coupled neural network segmentation. In the new method, uniform injection gains of each region are estimated through PCNN segmentation rather than through a simple square window. Since PCNN segmentation agrees with the human visual system, the proposed method shows better spectral consistency. Our experiments, which have been carried out for both suburban and urban datasets, demonstrate that the proposed method outperforms other methods in multispectral pansharpening.

PatterNet: a system to learn compact physical design pattern representations for pattern-based analytics

Science.gov (United States)

Lutich, Andrey

2017-07-01

This research considers the problem of generating compact vector representations of physical design patterns for analytics purposes in semiconductor patterning domain. PatterNet uses a deep artificial neural network to learn mapping of physical design patterns to a compact Euclidean hyperspace. Distances among mapped patterns in this space correspond to dissimilarities among patterns defined at the time of the network training. Once the mapping network has been trained, PatterNet embeddings can be used as feature vectors with standard machine learning algorithms, and pattern search, comparison, and clustering become trivial problems. PatterNet is inspired by the concepts developed within the framework of generative adversarial networks as well as the FaceNet. Our method facilitates a deep neural network (DNN) to learn directly the compact representation by supplying it with pairs of design patterns and dissimilarity among these patterns defined by a user. In the simplest case, the dissimilarity is represented by an area of the XOR of two patterns. Important to realize that our PatterNet approach is very different to the methods developed for deep learning on image data. In contrast to "conventional" pictures, the patterns in the CAD world are the lists of polygon vertex coordinates. The method solely relies on the promise of deep learning to discover internal structure of the incoming data and learn its hierarchical representations. Artificial intelligence arising from the combination of PatterNet and clustering analysis very precisely follows intuition of patterning/optical proximity correction experts paving the way toward human-like and human-friendly engineering tools.

Detecting Malware with an Ensemble Method Based on Deep Neural Network

Directory of Open Access Journals (Sweden)

Jinpei Yan

2018-01-01

Full Text Available Malware detection plays a crucial role in computer security. Recent researches mainly use machine learning based methods heavily relying on domain knowledge for manually extracting malicious features. In this paper, we propose MalNet, a novel malware detection method that learns features automatically from the raw data. Concretely, we first generate a grayscale image from malware file, meanwhile extracting its opcode sequences with the decompilation tool IDA. Then MalNet uses CNN and LSTM networks to learn from grayscale image and opcode sequence, respectively, and takes a stacking ensemble for malware classification. We perform experiments on more than 40,000 samples including 20,650 benign files collected from online software providers and 21,736 malwares provided by Microsoft. The evaluation result shows that MalNet achieves 99.88% validation accuracy for malware detection. In addition, we also take malware family classification experiment on 9 malware families to compare MalNet with other related works, in which MalNet outperforms most of related works with 99.36% detection accuracy and achieves a considerable speed-up on detecting efficiency comparing with two state-of-the-art results on Microsoft malware dataset.

Distant supervision for neural relation extraction integrated with word attention and property features.

Science.gov (United States)

Qu, Jianfeng; Ouyang, Dantong; Hua, Wen; Ye, Yuxin; Li, Ximing

2018-04-01

Distant supervision for neural relation extraction is an efficient approach to extracting massive relations with reference to plain texts. However, the existing neural methods fail to capture the critical words in sentence encoding and meanwhile lack useful sentence information for some positive training instances. To address the above issues, we propose a novel neural relation extraction model. First, we develop a word-level attention mechanism to distinguish the importance of each individual word in a sentence, increasing the attention weights for those critical words. Second, we investigate the semantic information from word embeddings of target entities, which can be developed as a supplementary feature for the extractor. Experimental results show that our model outperforms previous state-of-the-art baselines. Copyright © 2018 Elsevier Ltd. All rights reserved.

Decorrelated Jet Substructure Tagging using Adversarial Neural Networks

CERN Multimedia

CERN. Geneva

2017-01-01

We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved discovery significance relative to existing taggers. The network is trained using an adversarial strategy, resulting in a tagger that learns to balance classification accuracy with decorrelation. As a benchmark scenario, we consider the case where large-radius jets originating from a boosted Z' decay are discriminated from a background of nonresonant quark and gluon jets. We show that in the presence of systematic uncertainties on the background rate, our adversarially-trained, decorrelated tagger considerably outperforms a conventionally trained neural network, despite having a slightly worse signal-background separation power. We generalize the adversarial training technique to include a paramet...

Forecast of TEXT plasma disruptions using soft X-rays as input signal in a neural network

International Nuclear Information System (INIS)

Vannucci, A.; Oliveira, K.A.; Tajima, T.; Tajima, Y.J.

2001-01-01

A feed-forward neural network is used to forecast major and minor disruptions in TEXT tokamak discharges. Using the experimental data of soft X-ray signals as input data, the neural net is trained with one disruptive plasma discharge, while a different disruptive discharge is used for validation. After proper training, the net works with the same set of weights, it is then used to forecast disruptions in two other different plasma discharges. It is observed that the neural net is capable of predicting the onset of a disruption up to 3.12 ms in advance. From what we observe in the predictive behavior of our network, speculations are made whether the disruption triggering mechanism is associated with an increase in the m=2 magnetic island, that disturbs the central part of the plasma column afterwards, or the initial perturbation has first occurred in the central part of the plasma column and then the m=2 MHD mode is destabilized. (author)

Recursive Bayesian recurrent neural networks for time-series modeling.

Science.gov (United States)

Mirikitani, Derrick T; Nikolaev, Nikolay

2010-02-01

This paper develops a probabilistic approach to recursive second-order training of recurrent neural networks (RNNs) for improved time-series modeling. A general recursive Bayesian Levenberg-Marquardt algorithm is derived to sequentially update the weights and the covariance (Hessian) matrix. The main strengths of the approach are a principled handling of the regularization hyperparameters that leads to better generalization, and stable numerical performance. The framework involves the adaptation of a noise hyperparameter and local weight prior hyperparameters, which represent the noise in the data and the uncertainties in the model parameters. Experimental investigations using artificial and real-world data sets show that RNNs equipped with the proposed approach outperform standard real-time recurrent learning and extended Kalman training algorithms for recurrent networks, as well as other contemporary nonlinear neural models, on time-series modeling.

Hindcasting of storm waves using neural networks

Digital Repository Service at National Institute of Oceanography (India)

Rao, S.; Mandal, S.

Department NN neural network net i weighted sum of the inputs of neuron i o k network output at kth output node P total number of training pattern s i output of neuron i t k target output at kth output node 1. Introduction Severe storms occur in Bay of Bengal...), forecasting of runoff (Crespo and Mora, 1993), concrete strength (Kasperkiewicz et al., 1995). The uses of neural network in the coastal the wave conditions will change from year to year, thus a proper statistical and climatological treatment requires several...

Optimization of artificial neural networks for the reconstruction of the neutrons spectrum and their equivalent doses

International Nuclear Information System (INIS)

Reyes A, A.; Ortiz R, J. M.; Reyes H, A.; Castaneda M, R.; Solis S, L. O.; Vega C, H. R.

2014-08-01

In this work was used the robust design methodology of artificial neural networks to determine a good topology of net able to solve with efficiency the problems of neutrons spectrometry and dosimetry. For the design of the topology of optimized net 36 different net architectures based on an orthogonal arrangement with a configuration L 9 (3 4 ), L 4 (3 2 ) were trained. For the training of the neural networks, was used a computer code developed in the ambient of Mat lab programming, which automates the process and analysis of the information, reducing the time used in this activity considerably for the investigator. For the training of the propagation nets forward was utilized a neutrons spectrum compendium published by the International Atomic Energy Agency, where of the total 80% was used for the training and 20% for the test, it trained with an inverse propagation algorithm being the entrance data the count rates corresponding to the 7 spheres of the spectrometric system of Bonner spheres, as exit data, the neural network obtains the neutrons spectrum expressed in 60 energy groups and are calculated of simultaneous way 15 dosimetric quantities. (Author)

An Inventory Controlled Supply Chain Model Based on Improved BP Neural Network

Directory of Open Access Journals (Sweden)

Wei He

2013-01-01

Full Text Available Inventory control is a key factor for reducing supply chain cost and increasing customer satisfaction. However, prediction of inventory level is a challenging task for managers. As one of the widely used techniques for inventory control, standard BP neural network has such problems as low convergence rate and poor prediction accuracy. Aiming at these problems, a new fast convergent BP neural network model for predicting inventory level is developed in this paper. By adding an error offset, this paper deduces the new chain propagation rule and the new weight formula. This paper also applies the improved BP neural network model to predict the inventory level of an automotive parts company. The results show that the improved algorithm not only significantly exceeds the standard algorithm but also outperforms some other improved BP algorithms both on convergence rate and prediction accuracy.

A novel word spotting method based on recurrent neural networks.

Science.gov (United States)

Frinken, Volkmar; Fischer, Andreas; Manmatha, R; Bunke, Horst

2012-02-01

Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperform not only a classical dynamic time warping-based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition.

An assessment of the barriers to the consumers' uptake of genetically modified foods: a neural network analysis.

Science.gov (United States)

Rodríguez-Entrena, Macario; Salazar-Ordóñez, Melania; Becerra-Alonso, David

2016-03-30

This paper studies which of the attitudinal, cognitive and socio-economic factors determine the willingness to purchase genetically modified (GM) food, enabling the forecasting of consumers' behaviour in Andalusia, southern Spain. This classification has been made by a standard multilayer perceptron neural network trained with extreme learning machine. Later, an ordered logistic regression was applied to determine whether the neural network can outperform this traditional econometric approach. The results show that the highest relative contributions lie in the variables related to perceived risks of GM food, while the perceived benefits have a lower influence. In addition, an innovative attitude towards food presents a strong link, as does the perception of food safety. The variables with the least relative contribution are subjective knowledge about GM food and the consumers' age. The neural network approach outperforms the correct classification percentage from the ordered logistic regression. The perceived risks must be considered as a critical factor. A strategy to improve the GM food acceptance is to develop a transparent and balanced information framework that makes the potential risk understandable by society, and make them aware of the risk assessments for GM food in the EU. For its success, it is essential to improve the trust in EU institutions and scientific regulatory authorities. © 2015 Society of Chemical Industry.

An improved advertising CTR prediction approach based on the fuzzy deep neural network.

Science.gov (United States)

Jiang, Zilong; Gao, Shu; Li, Mingjiang

2018-01-01

Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR. The experimental results show that the proposed FDNN model outperforms several baseline models in terms of both data representation capability and robustness in advertising click log datasets with noise.

Neural Network with Local Memory for Nuclear Reactor Power Level Control

International Nuclear Information System (INIS)

Uluyol, Oender; Ragheb, Magdi; Tsoukalas, Lefteri

2001-01-01

A methodology is introduced for a neural network with local memory called a multilayered local output gamma feedback (LOGF) neural network within the paradigm of locally-recurrent globally-feedforward neural networks. It appears to be well-suited for the identification, prediction, and control tasks in highly dynamic systems; it allows for the presentation of different timescales through incorporation of a gamma memory. A learning algorithm based on the backpropagation-through-time approach is derived. The spatial and temporal weights of the network are iteratively optimized for a given problem using the derived learning algorithm. As a demonstration of the methodology, it is applied to the task of power level control of a nuclear reactor at different fuel cycle conditions. The results demonstrate that the LOGF neural network controller outperforms the classical as well as the state feedback-assisted classical controllers for reactor power level control by showing a better tracking of the demand power, improving the fuel and exit temperature responses, and by performing robustly in different fuel cycle and power level conditions

AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling.

Science.gov (United States)

Wang, Sheng; Sun, Siqi; Xu, Jinbo

2016-09-01

Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This paper presents Deep Convolutional Neural Fields (DeepCNF), an integration of DCNN with Conditional Random Field (CRF), for sequence labeling with an imbalanced label distribution. The widely-used training methods, such as maximum-likelihood and maximum labelwise accuracy, do not work well on imbalanced data. To handle this, we present a new training algorithm called maximum-AUC for DeepCNF. That is, we train DeepCNF by directly maximizing the empirical Area Under the ROC Curve (AUC), which is an unbiased measurement for imbalanced data. To fulfill this, we formulate AUC in a pairwise ranking framework, approximate it by a polynomial function and then apply a gradient-based procedure to optimize it. Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also has similar performance as the other two training methods on solvent accessibility prediction, which has three equally-distributed labels. Furthermore, our experimental results show that our AUC-trained DeepCNF models greatly outperform existing popular predictors of these three tasks. The data and software related to this paper are available at https://github.com/realbigws/DeepCNF_AUC.

Nonlinear signal processing using neural networks: Prediction and system modelling

Energy Technology Data Exchange (ETDEWEB)

Lapedes, A.; Farber, R.

1987-06-01

The backpropagation learning algorithm for neural networks is developed into a formalism for nonlinear signal processing. We illustrate the method by selecting two common topics in signal processing, prediction and system modelling, and show that nonlinear applications can be handled extremely well by using neural networks. The formalism is a natural, nonlinear extension of the linear Least Mean Squares algorithm commonly used in adaptive signal processing. Simulations are presented that document the additional performance achieved by using nonlinear neural networks. First, we demonstrate that the formalism may be used to predict points in a highly chaotic time series with orders of magnitude increase in accuracy over conventional methods including the Linear Predictive Method and the Gabor-Volterra-Weiner Polynomial Method. Deterministic chaos is thought to be involved in many physical situations including the onset of turbulence in fluids, chemical reactions and plasma physics. Secondly, we demonstrate the use of the formalism in nonlinear system modelling by providing a graphic example in which it is clear that the neural network has accurately modelled the nonlinear transfer function. It is interesting to note that the formalism provides explicit, analytic, global, approximations to the nonlinear maps underlying the various time series. Furthermore, the neural net seems to be extremely parsimonious in its requirements for data points from the time series. We show that the neural net is able to perform well because it globally approximates the relevant maps by performing a kind of generalized mode decomposition of the maps. 24 refs., 13 figs.

Bio-inspired Artificial Intelligence: А Generalized Net Model of the Regularization Process in MLP

Directory of Open Access Journals (Sweden)

Stanimir Surchev

2013-10-01

Full Text Available Many objects and processes inspired by the nature have been recreated by the scientists. The inspiration to create a Multilayer Neural Network came from human brain as member of the group. It possesses complicated structure and it is difficult to recreate, because of the existence of too many processes that require different solving methods. The aim of the following paper is to describe one of the methods that improve learning process of Artificial Neural Network. The proposed generalized net method presents Regularization process in Multilayer Neural Network. The purpose of verification is to protect the neural network from overfitting. The regularization is commonly used in neural network training process. Many methods of verification are present, the subject of interest is the one known as Regularization. It contains function in order to set weights and biases with smaller values to protect from overfitting.

Reciprocity Outperforms Conformity to Promote Cooperation.

Science.gov (United States)

Romano, Angelo; Balliet, Daniel

2017-10-01

Evolutionary psychologists have proposed two processes that could give rise to the pervasiveness of human cooperation observed among individuals who are not genetically related: reciprocity and conformity. We tested whether reciprocity outperformed conformity in promoting cooperation, especially when these psychological processes would promote a different cooperative or noncooperative response. To do so, across three studies, we observed participants' cooperation with a partner after learning (a) that their partner had behaved cooperatively (or not) on several previous trials and (b) that their group members had behaved cooperatively (or not) on several previous trials with that same partner. Although we found that people both reciprocate and conform, reciprocity has a stronger influence on cooperation. Moreover, we found that conformity can be partly explained by a concern about one's reputation-a finding that supports a reciprocity framework.

Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks.

Science.gov (United States)

Zazo, Ruben; Lozano-Diez, Alicia; Gonzalez-Dominguez, Javier; Toledano, Doroteo T; Gonzalez-Rodriguez, Joaquin

2016-01-01

Long Short Term Memory (LSTM) Recurrent Neural Networks (RNNs) have recently outperformed other state-of-the-art approaches, such as i-vector and Deep Neural Networks (DNNs), in automatic Language Identification (LID), particularly when dealing with very short utterances (∼3s). In this contribution we present an open-source, end-to-end, LSTM RNN system running on limited computational resources (a single GPU) that outperforms a reference i-vector system on a subset of the NIST Language Recognition Evaluation (8 target languages, 3s task) by up to a 26%. This result is in line with previously published research using proprietary LSTM implementations and huge computational resources, which made these former results hardly reproducible. Further, we extend those previous experiments modeling unseen languages (out of set, OOS, modeling), which is crucial in real applications. Results show that a LSTM RNN with OOS modeling is able to detect these languages and generalizes robustly to unseen OOS languages. Finally, we also analyze the effect of even more limited test data (from 2.25s to 0.1s) proving that with as little as 0.5s an accuracy of over 50% can be achieved.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Directory of Open Access Journals (Sweden)

Francisco Javier Ordóñez

2016-01-01

Full Text Available Human activity recognition (HAR tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i is suitable for multimodal wearable sensors; (ii can perform sensor fusion naturally; (iii does not require expert knowledge in designing features; and (iv explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-18

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters' influence on performance to provide insights about their optimisation.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-01

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation. PMID:26797612

Acoustic Event Detection in Multichannel Audio Using Gated Recurrent Neural Networks with High‐Resolution Spectral Features

Directory of Open Access Journals (Sweden)

Hyoung‐Gook Kim

2017-12-01

Full Text Available Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception‐based spatial and spectral‐domain noise‐reduced harmonic features are extracted from multichannel audio and used as high‐resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short‐term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches.

Neural network algorithm for image reconstruction using the grid friendly projections

International Nuclear Information System (INIS)

Cierniak, R.

2011-01-01

Full text: The presented paper describes a development of original approach to the reconstruction problem using a recurrent neural network. Particularly, the 'grid-friendly' angles of performed projections are selected according to the discrete Radon transform (DRT) concept to decrease the number of projections required. The methodology of our approach is consistent with analytical reconstruction algorithms. Reconstruction problem is reformulated in our approach to optimization problem. This problem is solved in present concept using method based on the maximum likelihood methodology. The reconstruction algorithm proposed in this work is consequently adapted for more practical discrete fan beam projections. Computer simulation results show that the neural network reconstruction algorithm designed to work in this way improves obtained results and outperforms conventional methods in reconstructed image quality. (author)

Thermal photovoltaic solar integrated system analysis using neural networks

Energy Technology Data Exchange (ETDEWEB)

Ashhab, S. [Hashemite Univ., Zarqa (Jordan). Dept. of Mechanical Engineering

2007-07-01

The energy demand in Jordan is primarily met by petroleum products. As such, the development of renewable energy systems is quite attractive. In particular, solar energy is a promising renewable energy source in Jordan and has been used for food canning, paper production, air-conditioning and sterilization. Artificial neural networks (ANNs) have received significant attention due to their capabilities in forecasting, modelling of complex nonlinear systems and control. ANNs have been used for forecasting solar energy. This paper presented a study that examined a thermal photovoltaic solar integrated system that was built in Jordan. Historical input-output system data that was collected experimentally was used to train an ANN that predicted the collector, PV module, pump and total efficiencies. The model predicted the efficiencies well and can therefore be utilized to find the operating conditions of the system that will produce the maximum system efficiencies. The paper provided a description of the photovoltaic solar system including equations for PV module efficiency; pump efficiency; and total efficiency. The paper also presented data relevant to the system performance and neural networks. The results of a neural net model were also presented based on the thermal PV solar integrated system data that was collected. It was concluded that the neural net model of the thermal photovoltaic solar integrated system set the background for achieving the best system performance. 10 refs., 6 figs.

Automatic slice identification in 3D medical images with a ConvNet regressor

NARCIS (Netherlands)

de Vos, Bob D.; Viergever, Max A.; de Jong, Pim A.; Išgum, Ivana

2016-01-01

Identification of anatomical regions of interest is a prerequisite in many medical image analysis tasks. We propose a method that automatically identifies a slice of interest (SOI) in 3D images with a convolutional neural network (ConvNet) regressor. In 150 chest CT scans two reference slices were

Developing Scene Understanding Neural Software for Realistic Autonomous Outdoor Missions

Science.gov (United States)

2017-09-01

computer using a single graphics processing unit (GPU). To the best of our knowledge, an implementation of the open-source Python -based AlexNet CNN on...1. Introduction Neurons in the brain enable us to understand scenes by assessing the spatial, temporal, and feature relations of objects in the...effort to use computer neural networks to augment human neural intelligence to improve our scene understanding (Krizhevsky et al. 2012; Zhou et al

Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields.

Science.gov (United States)

Wang, Sheng; Peng, Jian; Ma, Jianzhu; Xu, Jinbo

2016-01-11

Protein secondary structure (SS) prediction is important for studying protein structure and function. When only the sequence (profile) information is used as input feature, currently the best predictors can obtain ~80% Q3 accuracy, which has not been improved in the past decade. Here we present DeepCNF (Deep Convolutional Neural Fields) for protein SS prediction. DeepCNF is a Deep Learning extension of Conditional Neural Fields (CNF), which is an integration of Conditional Random Fields (CRF) and shallow neural networks. DeepCNF can model not only complex sequence-structure relationship by a deep hierarchical architecture, but also interdependency between adjacent SS labels, so it is much more powerful than CNF. Experimental results show that DeepCNF can obtain ~84% Q3 accuracy, ~85% SOV score, and ~72% Q8 accuracy, respectively, on the CASP and CAMEO test proteins, greatly outperforming currently popular predictors. As a general framework, DeepCNF can be used to predict other protein structure properties such as contact number, disorder regions, and solvent accessibility.

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT.

Science.gov (United States)

Han, Yoseob; Ye, Jong Chul

2018-06-01

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance.

Identification of phosphorylation sites in protein kinase A substrates using artificial neural networks and mass spectrometry

DEFF Research Database (Denmark)

Hjerrild, M.; Stensballe, A.; Rasmussen, T.E.

2004-01-01

Protein phosphorylation plays a key role in cell regulation and identification of phosphorylation sites is important for understanding their functional significance. Here, we present an artificial neural network algorithm: NetPhosK (http://www.cbs.dtu.dk/services/NetPhosK/) that predicts protein...

Identification of phosphorylation sites in protein kinase A substrates using artificial neural networks and mass spectrometry

DEFF Research Database (Denmark)

Hjerrild, Majbrit; Stensballe, Allan; Rasmussen, Thomas E

2011-01-01

Protein phosphorylation plays a key role in cell regulation and identification of phosphorylation sites is important for understanding their functional significance. Here, we present an artificial neural network algorithm: NetPhosK (http://www.cbs.dtu.dk/services/NetPhosK/) that predicts protein...

A novel low-voltage low-power analogue VLSI implementation of neural networks with on-chip back-propagation learning

Science.gov (United States)

Carrasco, Manuel; Garde, Andres; Murillo, Pilar; Serrano, Luis

2005-06-01

In this paper a novel design and implementation of a VLSI Analogue Neural Net based on Multi-Layer Perceptron (MLP) with on-chip Back Propagation (BP) learning algorithm suitable for the resolution of classification problems is described. In order to implement a general and programmable analogue architecture, the design has been carried out in a hierarchical way. In this way the net has been divided in synapsis-blocks and neuron-blocks providing an easy method for the analysis. These blocks basically consist on simple cells, which are mainly, the activation functions (NAF), derivatives (DNAF), multipliers and weight update circuits. The analogue design is based on current-mode translinear techniques using MOS transistors working in the weak inversion region in order to reduce both the voltage supply and the power consumption. Moreover, with the purpose of minimizing the noise, offset and distortion of even order, the topologies are fully-differential and balanced. The circuit, named ANNE (Analogue Neural NEt), has been prototyped and characterized as a proof of concept on CMOS AMI-0.5A technology occupying a total area of 2.7mm2. The chip includes two versions of neural nets with on-chip BP learning algorithm, which are respectively a 2-1 and a 2-2-1 implementations. The proposed nets have been experimentally tested using supply voltages from 2.5V to 1.8V, which is suitable for single cell lithium-ion battery supply applications. Experimental results of both implementations included in ANNE exhibit a good performance on solving classification problems. These results have been compared with other proposed Analogue VLSI implementations of Neural Nets published in the literature demonstrating that our proposal is very efficient in terms of occupied area and power consumption.

Neural nets with varying topology for high energy particle recognition. Theory and applications

International Nuclear Information System (INIS)

Perrone, A.L.; Basti, G.; Messi, R.; Paoluzi, L.; Picozza, P.

1995-01-01

In this paper we propose a strategy to solve the problem of parallel compuation based on a dynamic definition of the net topology showing its effectiveness for problems of particle track recognition in high-energy physics. In this way, we can maintain the linear architecture like in the geometric perceptron, but with a partial and dynamic connectivity so to overcome the intrinsic limiations of the geometric perceptron. Namely, the computation is truly parallel because of the partial connectivity but the net topology is always the optimal one because of its dynamic redefinition on the single input pattern. For these properties, we call this new architecture dynamic perceptron

Convolutional Neural Network for Histopathological Analysis of Osteosarcoma.

Science.gov (United States)

Mishra, Rashika; Daescu, Ovidiu; Leavey, Patrick; Rakheja, Dinesh; Sengupta, Anita

2018-03-01

Pathologists often deal with high complexity and sometimes disagreement over osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is a challenging task because of intra-class variations, inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis. In this article, we propose convolutional neural network (CNN) as a tool to improve efficiency and accuracy of osteosarcoma tumor classification into tumor classes (viable tumor, necrosis) versus nontumor. The proposed CNN architecture contains eight learned layers: three sets of stacked two convolutional layers interspersed with max pooling layers for feature extraction and two fully connected layers with data augmentation strategies to boost performance. The use of a neural network results in higher accuracy of average 92% for the classification. We compare the proposed architecture with three existing and proven CNN architectures for image classification: AlexNet, LeNet, and VGGNet. We also provide a pipeline to calculate percentage necrosis in a given whole slide image. We conclude that the use of neural networks can assure both high accuracy and efficiency in osteosarcoma classification.

ISTA-Net: Iterative Shrinkage-Thresholding Algorithm Inspired Deep Network for Image Compressive Sensing

KAUST Repository

Zhang, Jian

2017-06-24

Traditional methods for image compressive sensing (CS) reconstruction solve a well-defined inverse problem that is based on a predefined CS model, which defines the underlying structure of the problem and is generally solved by employing convergent iterative solvers. These optimization-based CS methods face the challenge of choosing optimal transforms and tuning parameters in their solvers, while also suffering from high computational complexity in most cases. Recently, some deep network based CS algorithms have been proposed to improve CS reconstruction performance, while dramatically reducing time complexity as compared to optimization-based methods. Despite their impressive results, the proposed networks (either with fully-connected or repetitive convolutional layers) lack any structural diversity and they are trained as a black box, void of any insights from the CS domain. In this paper, we combine the merits of both types of CS methods: the structure insights of optimization-based method and the performance/speed of network-based ones. We propose a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $l_1$ norm CS reconstruction model. ISTA-Net essentially implements a truncated form of ISTA, where all ISTA-Net parameters are learned end-to-end to minimize a reconstruction error in training. Borrowing more insights from the optimization realm, we propose an accelerated version of ISTA-Net, dubbed FISTA-Net, which is inspired by the fast iterative shrinkage-thresholding algorithm (FISTA). Interestingly, this acceleration naturally leads to skip connections in the underlying network design. Extensive CS experiments demonstrate that the proposed ISTA-Net and FISTA-Net outperform existing optimization-based and network-based CS methods by large margins, while maintaining a fast runtime.

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

International Nuclear Information System (INIS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-01-01

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

Science.gov (United States)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solis Sanches, L. O.; Miranda, R. Castaneda; Cervantes Viramontes, J. M. [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica. Av. Ramon Lopez Velarde 801. Col. Centro Zacatecas, Zac (Mexico); Vega-Carrillo, H. R. [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica. Av. Ramon Lopez Velarde 801. Col. Centro Zacatecas, Zac., Mexico. and Unidad Academica de Estudios Nucleares. C. Cip (Mexico)

2013-07-03

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in

Visualizing deep neural network by alternately image blurring and deblurring.

Science.gov (United States)

Wang, Feng; Liu, Haijun; Cheng, Jian

2018-01-01

Visualization from trained deep neural networks has drawn massive public attention in recent. One of the visualization approaches is to train images maximizing the activation of specific neurons. However, directly maximizing the activation would lead to unrecognizable images, which cannot provide any meaningful information. In this paper, we introduce a simple but effective technique to constrain the optimization route of the visualization. By adding two totally inverse transformations, image blurring and deblurring, to the optimization procedure, recognizable images can be created. Our algorithm is good at extracting the details in the images, which are usually filtered by previous methods in the visualizations. Extensive experiments on AlexNet, VGGNet and GoogLeNet illustrate that we can better understand the neural networks utilizing the knowledge obtained by the visualization. Copyright © 2017 Elsevier Ltd. All rights reserved.

predicting water levels at kainji dam using artificial neural networks

African Journals Online (AJOL)

2013-03-01

Mar 1, 2013 ... Apart from insufficient number of power generation plants, existing ones are ... ture and/or functional aspects of biological neural net-. Nigerian Journal of ... Their model used the radiosonde-based 700-hPa wind direction and ...

ObamaNet: Photo-realistic lip-sync from text

OpenAIRE

Kumar, Rithesh; Sotelo, Jose; Kumar, Kundan; de Brebisson, Alexandre; Bengio, Yoshua

2017-01-01

We present ObamaNet, the first architecture that generates both audio and synchronized photo-realistic lip-sync videos from any new text. Contrary to other published lip-sync approaches, ours is only composed of fully trainable neural modules and does not rely on any traditional computer graphics methods. More precisely, we use three main modules: a text-to-speech network based on Char2Wav, a time-delayed LSTM to generate mouth-keypoints synced to the audio, and a network based on Pix2Pix to ...

Built-in self-repair of VLSI memories employing neural nets

Science.gov (United States)

Mazumder, Pinaki

1998-10-01

The decades of the Eighties and the Nineties have witnessed the spectacular growth of VLSI technology, when the chip size has increased from a few hundred devices to a staggering multi-millon transistors. This trend is expected to continue as the CMOS feature size progresses towards the nanometric dimension of 100 nm and less. SIA roadmap projects that, where as the DRAM chips will integrate over 20 billion devices in the next millennium, the future microprocessors may incorporate over 100 million transistors on a single chip. As the VLSI chip size increase, the limited accessibility of circuit components poses great difficulty for external diagnosis and replacement in the presence of faulty components. For this reason, extensive work has been done in built-in self-test techniques, but little research is known concerning built-in self-repair. Moreover, the extra hardware introduced by conventional fault-tolerance techniques is also likely to become faulty, therefore causing the circuit to be useless. This research demonstrates the feasibility of implementing electronic neural networks as intelligent hardware for memory array repair. Most importantly, we show that the neural network control possesses a robust and degradable computing capability under various fault conditions. Overall, a yield analysis performed on 64K DRAM's shows that the yield can be improved from as low as 20 percent to near 99 percent due to the self-repair design, with overhead no more than 7 percent.

Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images.

Science.gov (United States)

Johnson, J L

1994-09-10

The linking-field neural network model of Eckhorn et al. [Neural Comput. 2, 293-307 (1990)] was introduced to explain the experimentally observed synchronous activity among neural assemblies in the cat cortex induced by feature-dependent visual activity. The model produces synchronous bursts of pulses from neurons with similar activity, effectively grouping them by phase and pulse frequency. It gives a basic new function: grouping by similarity. The synchronous bursts are obtained in the limit of strong linking strengths. The linking-field model in the limit of moderate-to-weak linking characterized by few if any multiple bursts is investigated. In this limit dynamic, locally periodic traveling waves exist whose time signal encodes the geometrical structure of a two-dimensional input image. The signal can be made insensitive to translation, scale, rotation, distortion, and intensity. The waves transmit information beyond the physical interconnect distance. The model is implemented in an optical hybrid demonstration system. Results of the simulations and the optical system are presented.

Automatic target recognition using a feature-based optical neural network

Science.gov (United States)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Explicitly integrating parameter, input, and structure uncertainties into Bayesian Neural Networks for probabilistic hydrologic forecasting

KAUST Repository

Zhang, Xuesong

2011-11-01

Estimating uncertainty of hydrologic forecasting is valuable to water resources and other relevant decision making processes. Recently, Bayesian Neural Networks (BNNs) have been proved powerful tools for quantifying uncertainty of streamflow forecasting. In this study, we propose a Markov Chain Monte Carlo (MCMC) framework (BNN-PIS) to incorporate the uncertainties associated with parameters, inputs, and structures into BNNs. This framework allows the structure of the neural networks to change by removing or adding connections between neurons and enables scaling of input data by using rainfall multipliers. The results show that the new BNNs outperform BNNs that only consider uncertainties associated with parameters and model structures. Critical evaluation of posterior distribution of neural network weights, number of effective connections, rainfall multipliers, and hyper-parameters shows that the assumptions held in our BNNs are not well supported. Further understanding of characteristics of and interactions among different uncertainty sources is expected to enhance the application of neural networks for uncertainty analysis of hydrologic forecasting. © 2011 Elsevier B.V.

Classifying images using restricted Boltzmann machines and convolutional neural networks

Science.gov (United States)

Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

2017-07-01

To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

Neural-network classifiers for automatic real-world aerial image recognition

Science.gov (United States)

Greenberg, Shlomo; Guterman, Hugo

1996-08-01

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

Probing many-body localization with neural networks

Science.gov (United States)

Schindler, Frank; Regnault, Nicolas; Neupert, Titus

2017-06-01

We show that a simple artificial neural network trained on entanglement spectra of individual states of a many-body quantum system can be used to determine the transition between a many-body localized and a thermalizing regime. Specifically, we study the Heisenberg spin-1/2 chain in a random external field. We employ a multilayer perceptron with a single hidden layer, which is trained on labeled entanglement spectra pertaining to the fully localized and fully thermal regimes. We then apply this network to classify spectra belonging to states in the transition region. For training, we use a cost function that contains, in addition to the usual error and regularization parts, a term that favors a confident classification of the transition region states. The resulting phase diagram is in good agreement with the one obtained by more conventional methods and can be computed for small systems. In particular, the neural network outperforms conventional methods in classifying individual eigenstates pertaining to a single disorder realization. It allows us to map out the structure of these eigenstates across the transition with spatial resolution. Furthermore, we analyze the network operation using the dreaming technique to show that the neural network correctly learns by itself the power-law structure of the entanglement spectra in the many-body localized regime.

Neural-net predictor for beta limit disruptions in JT-60U

International Nuclear Information System (INIS)

Yoshino, R.

2005-01-01

Prediction of major disruptions occurring at the β -limit for tokamak plasmas with a normal magnetic shear in JT-60U was conducted using neural networks. Since no clear precursors are generally observed a few tens of milliseconds before the β -limit disruption, a sub-neural network is trained to output the value of the β N limit every 2 ms. The target β N limit is artificially set by the operator in the first step to train a network with non-disruptive shots as well as disruptive shots, and then in the second step the target limit is modified using the β N limit output from the trained network. The adjusted target greatly improves the consistency between the input data and the output. This training, the 'self-teaching method', has greatly reduced the false alarm rate triggered for non-disruptive shots. To improve the prediction performance further, the difference between the output β N limit and the measured β N , and 11 parameters, are inputted to the main neural network to calculate the 'stability level'. The occurrence of a major disruption is predicted when the stability level decreases to the 'alarm level'. Major disruptions at the β -limit have been predicted by the main network with a prediction success rate of 80% at 10 ms prior to the disruption while the false alarm rate is lower than 4% for non-disruptive shots. This 80% value is much higher than that obtained for a network trained with a fixed target β N limit set to be the maximum β N observed at the start of a major disruption, lower than 10%. A prediction success rate of 90% with a false alarm rate of 12% at 10 ms prior to the disruption has also been obtained. This 12% value is about half of that obtained for a network trained with a fixed target β N limit

Neural Networks for Self-tuning Control Systems

Directory of Open Access Journals (Sweden)

A. Noriega Ponce

2004-01-01

Full Text Available In this paper, we presented a self-tuning control algorithm based on a three layers perceptron type neural network. The proposed algorithm is advantageous in the sense that practically a previous training of the net is not required and some changes in the set-point are generally enough to adjust the learning coefficient. Optionally, it is possible to introduce a self-tuning mechanism of the learning coefficient although by the moment it is not possible to give final conclusions about this possibility. The proposed algorithm has the special feature that the regulation error instead of the net output error is retropropagated for the weighting coefficients modifications. 

Petri neural network model for the effect of controlled thermomechanical process parameters on the mechanical properties of HSLA steels

Energy Technology Data Exchange (ETDEWEB)

Datta, S.

1999-10-01

The effect of composition and controlled thermomechanical process parameters on the mechanical properties of HSLA steels is modelled using the Widrow-Hoff's concept of training a neural net with feed-forward topology by applying Rumelhart's back propagation type algorithm for supervised learning, using a Petri like net structure. The data used are from laboratory experiments as well as from the published literature. The results from the neural network are found to be consistent and in good agreement with the experimented results. (author)

Classifying medical relations in clinical text via convolutional neural networks.

Science.gov (United States)

He, Bin; Guan, Yi; Dai, Rui

2018-05-16

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method. Copyright © 2018. Published by Elsevier B.V.

Optimization of the kernel functions in a probabilistic neural network analyzing the local pattern distribution.

Science.gov (United States)

Galleske, I; Castellanos, J

2002-05-01

This article proposes a procedure for the automatic determination of the elements of the covariance matrix of the gaussian kernel function of probabilistic neural networks. Two matrices, a rotation matrix and a matrix of variances, can be calculated by analyzing the local environment of each training pattern. The combination of them will form the covariance matrix of each training pattern. This automation has two advantages: First, it will free the neural network designer from indicating the complete covariance matrix, and second, it will result in a network with better generalization ability than the original model. A variation of the famous two-spiral problem and real-world examples from the UCI Machine Learning Repository will show a classification rate not only better than the original probabilistic neural network but also that this model can outperform other well-known classification techniques.

Deep nets vs expert designed features in medical physics: An IMRT QA case study.

Science.gov (United States)

Interian, Yannet; Rideout, Vincent; Kearney, Vasant P; Gennatas, Efstathios; Morin, Olivier; Cheung, Joey; Solberg, Timothy; Valdes, Gilmer

2018-03-30

The purpose of this study was to compare the performance of Deep Neural Networks against a technique designed by domain experts in the prediction of gamma passing rates for Intensity Modulated Radiation Therapy Quality Assurance (IMRT QA). A total of 498 IMRT plans across all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam Linacs. Measurements were performed using a commercial 2D diode array, and passing rates for 3%/3 mm local dose/distance-to-agreement (DTA) were recorded. Separately, fluence maps calculated for each plan were used as inputs to a convolution neural network (CNN). The CNNs were trained to predict IMRT QA gamma passing rates using TensorFlow and Keras. A set of model architectures, inspired by the convolutional blocks of the VGG-16 ImageNet model, were constructed and implemented. Synthetic data, created by rotating and translating the fluence maps during training, was created to boost the performance of the CNNs. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to a generalized Poisson regression model, previously developed for this application, which used 78 expert designed features. Deep Neural Networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts in the prediction of 3%/3 mm Local gamma passing rates. An ensemble of neural nets resulted in a mean absolute error (MAE) of 0.70 ± 0.05 and the domain expert model resulted in a 0.74 ± 0.06. Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts. © 2018 American Association of Physicists in Medicine.

Discriminative Elastic-Net Regularized Linear Regression.

Science.gov (United States)

Zhang, Zheng; Lai, Zhihui; Xu, Yong; Shao, Ling; Wu, Jian; Xie, Guo-Sen

2017-03-01

In this paper, we aim at learning compact and discriminative linear regression models. Linear regression has been widely used in different problems. However, most of the existing linear regression methods exploit the conventional zero-one matrix as the regression targets, which greatly narrows the flexibility of the regression model. Another major limitation of these methods is that the learned projection matrix fails to precisely project the image features to the target space due to their weak discriminative capability. To this end, we present an elastic-net regularized linear regression (ENLR) framework, and develop two robust linear regression models which possess the following special characteristics. First, our methods exploit two particular strategies to enlarge the margins of different classes by relaxing the strict binary targets into a more feasible variable matrix. Second, a robust elastic-net regularization of singular values is introduced to enhance the compactness and effectiveness of the learned projection matrix. Third, the resulting optimization problem of ENLR has a closed-form solution in each iteration, which can be solved efficiently. Finally, rather than directly exploiting the projection matrix for recognition, our methods employ the transformed features as the new discriminate representations to make final image classification. Compared with the traditional linear regression model and some of its variants, our method is much more accurate in image classification. Extensive experiments conducted on publicly available data sets well demonstrate that the proposed framework can outperform the state-of-the-art methods. The MATLAB codes of our methods can be available at http://www.yongxu.org/lunwen.html.

SCYNet. Testing supersymmetric models at the LHC with neural networks

Energy Technology Data Exchange (ETDEWEB)

Bechtle, Philip; Belkner, Sebastian; Hamer, Matthias [Universitaet Bonn, Bonn (Germany); Dercks, Daniel [Universitaet Hamburg, Hamburg (Germany); Keller, Tim; Kraemer, Michael; Sarrazin, Bjoern; Schuette-Engel, Jan; Tattersall, Jamie [RWTH Aachen University, Institute for Theoretical Particle Physics and Cosmology, Aachen (Germany)

2017-10-15

SCYNet (SUSY Calculating Yield Net) is a tool for testing supersymmetric models against LHC data. It uses neural network regression for a fast evaluation of the profile likelihood ratio. Two neural network approaches have been developed: one network has been trained using the parameters of the 11-dimensional phenomenological Minimal Supersymmetric Standard Model (pMSSM-11) as an input and evaluates the corresponding profile likelihood ratio within milliseconds. It can thus be used in global pMSSM-11 fits without time penalty. In the second approach, the neural network has been trained using model-independent signature-related objects, such as energies and particle multiplicities, which were estimated from the parameters of a given new physics model. (orig.)

Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks

Science.gov (United States)

Ienco, Dino; Gaetano, Raffaele; Dupaquier, Claire; Maurel, Pierre

2017-10-01

Nowadays, modern earth observation programs produce huge volumes of satellite images time series (SITS) that can be useful to monitor geographical areas through time. How to efficiently analyze such kind of information is still an open question in the remote sensing field. Recently, deep learning methods proved suitable to deal with remote sensing data mainly for scene classification (i.e. Convolutional Neural Networks - CNNs - on single images) while only very few studies exist involving temporal deep learning approaches (i.e Recurrent Neural Networks - RNNs) to deal with remote sensing time series. In this letter we evaluate the ability of Recurrent Neural Networks, in particular the Long-Short Term Memory (LSTM) model, to perform land cover classification considering multi-temporal spatial data derived from a time series of satellite images. We carried out experiments on two different datasets considering both pixel-based and object-based classification. The obtained results show that Recurrent Neural Networks are competitive compared to state-of-the-art classifiers, and may outperform classical approaches in presence of low represented and/or highly mixed classes. We also show that using the alternative feature representation generated by LSTM can improve the performances of standard classifiers.

Enhancement of digital radiography image quality using a convolutional neural network.

Science.gov (United States)

Sun, Yuewen; Li, Litao; Cong, Peng; Wang, Zhentao; Guo, Xiaojing

2017-01-01

Digital radiography system is widely used for noninvasive security check and medical imaging examination. However, the system has a limitation of lower image quality in spatial resolution and signal to noise ratio. In this study, we explored whether the image quality acquired by the digital radiography system can be improved with a modified convolutional neural network to generate high-resolution images with reduced noise from the original low-quality images. The experiment evaluated on a test dataset, which contains 5 X-ray images, showed that the proposed method outperformed the traditional methods (i.e., bicubic interpolation and 3D block-matching approach) as measured by peak signal to noise ratio (PSNR) about 1.3 dB while kept highly efficient processing time within one second. Experimental results demonstrated that a residual to residual (RTR) convolutional neural network remarkably improved the image quality of object structural details by increasing the image resolution and reducing image noise. Thus, this study indicated that applying this RTR convolutional neural network system was useful to improve image quality acquired by the digital radiography system.

Automated Understanding of Financial Statements Using Neural Networks and Semantic Grammars

OpenAIRE

Markovitch, J. S.

1995-01-01

This article discusses how neural networks and semantic grammars may be used to locate and understand financial statements embedded in news stories received from on-line news wires. A neural net is used to identify where in the news story a financial statement appears to begin. A grammar then is applied to this text in an effort to extract specific facts from the financial statement. Applying grammars to financial statements presents unique parsing problems since the dollar amounts of financi...

Neural estimation of kinetic rate constants from dynamic PET-scans

DEFF Research Database (Denmark)

Fog, Torben L.; Nielsen, Lars Hupfeldt; Hansen, Lars Kai

1994-01-01

A feedforward neural net is trained to invert a simple three compartment model describing the tracer kinetics involved in the metabolism of [18F]fluorodeoxyglucose in the human brain. The network can estimate rate constants from positron emission tomography sequences and is about 50 times faster ...

A convolutional neural network neutrino event classifier

International Nuclear Information System (INIS)

Aurisano, A.; Sousa, A.; Radovic, A.; Vahle, P.; Rocco, D.; Pawloski, G.; Himmel, A.; Niner, E.; Messier, M.D.; Psihas, F.

2016-01-01

Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

Investment Valuation Analysis with Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Hüseyin İNCE

2017-07-01

Full Text Available This paper shows that discounted cash flow and net present value, which are traditional investment valuation models, can be combined with artificial neural network model forecasting. The main inputs for the valuation models, such as revenue, costs, capital expenditure, and their growth rates, are heavily related to sector dynamics and macroeconomics. The growth rates of those inputs are related to inflation and exchange rates. Therefore, predicting inflation and exchange rates is a critical issue for the valuation output. In this paper, the Turkish economy’s inflation rate and the exchange rate of USD/TRY are forecast by artificial neural networks and implemented to the discounted cash flow model. Finally, the results are benchmarked with conventional practices.

Application and Simulation of Fuzzy Neural Network PID Controller in the Aircraft Cabin Temperature

Directory of Open Access Journals (Sweden)

Ding Fang

2013-06-01

Full Text Available Considering complex factors of affecting ambient temperature in Aircraft cabin, and some shortages of traditional PID control like the parameters difficult to be tuned and control ineffective, this paper puts forward the intelligent PID algorithm that makes fuzzy logic method and neural network together, scheming out the fuzzy neural net PID controller. After the correction of the fuzzy inference and dynamic learning of neural network, PID parameters of the controller get the optimal parameters. MATLAB simulation results of the cabin temperature control model show that the performance of the fuzzy neural network PID controller has been greatly improved, with faster response, smaller overshoot and better adaptability.

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods.

Science.gov (United States)

Arcos-García, Álvaro; Álvarez-García, Juan A; Soria-Morillo, Luis M

2018-03-01

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements. Copyright © 2018 Elsevier Ltd. All rights reserved.

Confidence limits for data mining models of options prices

Science.gov (United States)

Healy, J. V.; Dixon, M.; Read, B. J.; Cai, F. F.

2004-12-01

Non-parametric methods such as artificial neural nets can successfully model prices of financial options, out-performing the Black-Scholes analytic model (Eur. Phys. J. B 27 (2002) 219). However, the accuracy of such approaches is usually expressed only by a global fitting/error measure. This paper describes a robust method for determining prediction intervals for models derived by non-linear regression. We have demonstrated it by application to a standard synthetic example (29th Annual Conference of the IEEE Industrial Electronics Society, Special Session on Intelligent Systems, pp. 1926-1931). The method is used here to obtain prediction intervals for option prices using market data for LIFFE “ESX” FTSE 100 index options ( http://www.liffe.com/liffedata/contracts/month_onmonth.xls). We avoid special neural net architectures and use standard regression procedures to determine local error bars. The method is appropriate for target data with non constant variance (or volatility).

Stochastic gradient ascent outperforms gamers in the Quantum Moves game

Science.gov (United States)

Sels, Dries

2018-04-01

In a recent work on quantum state preparation, Sørensen and co-workers [Nature (London) 532, 210 (2016), 10.1038/nature17620] explore the possibility of using video games to help design quantum control protocols. The authors present a game called "Quantum Moves" (https://www.scienceathome.org/games/quantum-moves/) in which gamers have to move an atom from A to B by means of optical tweezers. They report that, "players succeed where purely numerical optimization fails." Moreover, by harnessing the player strategies, they can "outperform the most prominent established numerical methods." The aim of this Rapid Communication is to analyze the problem in detail and show that those claims are untenable. In fact, without any prior knowledge and starting from a random initial seed, a simple stochastic local optimization method finds near-optimal solutions which outperform all players. Counterdiabatic driving can even be used to generate protocols without resorting to numeric optimization. The analysis results in an accurate analytic estimate of the quantum speed limit which, apart from zero-point motion, is shown to be entirely classical in nature. The latter might explain why gamers are reasonably good at the game. A simple modification of the BringHomeWater challenge is proposed to test this hypothesis.

Classification of breast cancer cytological specimen using convolutional neural network

Science.gov (United States)

Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

2017-01-01

The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

Radio frequency interference mitigation using deep convolutional neural networks

Science.gov (United States)

Akeret, J.; Chang, C.; Lucchi, A.; Refregier, A.

2017-01-01

We propose a novel approach for mitigating radio frequency interference (RFI) signals in radio data using the latest advances in deep learning. We employ a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. We train and assess the performance of this network using the HIDE &SEEK radio data simulation and processing packages, as well as early Science Verification data acquired with the 7m single-dish telescope at the Bleien Observatory. We find that our U-Net implementation is showing competitive accuracy to classical RFI mitigation algorithms such as SEEK's SUMTHRESHOLD implementation. We publish our U-Net software package on GitHub under GPLv3 license.

File access prediction using neural networks.

Science.gov (United States)

Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar

2010-06-01

One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors.

Event- and Time-Driven Techniques Using Parallel CPU-GPU Co-processing for Spiking Neural Networks.

Science.gov (United States)

Naveros, Francisco; Garrido, Jesus A; Carrillo, Richard R; Ros, Eduardo; Luque, Niceto R

2017-01-01

Modeling and simulating the neural structures which make up our central neural system is instrumental for deciphering the computational neural cues beneath. Higher levels of biological plausibility usually impose higher levels of complexity in mathematical modeling, from neural to behavioral levels. This paper focuses on overcoming the simulation problems (accuracy and performance) derived from using higher levels of mathematical complexity at a neural level. This study proposes different techniques for simulating neural models that hold incremental levels of mathematical complexity: leaky integrate-and-fire (LIF), adaptive exponential integrate-and-fire (AdEx), and Hodgkin-Huxley (HH) neural models (ranged from low to high neural complexity). The studied techniques are classified into two main families depending on how the neural-model dynamic evaluation is computed: the event-driven or the time-driven families. Whilst event-driven techniques pre-compile and store the neural dynamics within look-up tables, time-driven techniques compute the neural dynamics iteratively during the simulation time. We propose two modifications for the event-driven family: a look-up table recombination to better cope with the incremental neural complexity together with a better handling of the synchronous input activity. Regarding the time-driven family, we propose a modification in computing the neural dynamics: the bi-fixed-step integration method. This method automatically adjusts the simulation step size to better cope with the stiffness of the neural model dynamics running in CPU platforms. One version of this method is also implemented for hybrid CPU-GPU platforms. Finally, we analyze how the performance and accuracy of these modifications evolve with increasing levels of neural complexity. We also demonstrate how the proposed modifications which constitute the main contribution of this study systematically outperform the traditional event- and time-driven techniques under

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

Science.gov (United States)

Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

2017-09-01

Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN

Similar patterns of neural activity predict memory function during encoding and retrieval.

Science.gov (United States)

Kragel, James E; Ezzyat, Youssef; Sperling, Michael R; Gorniak, Richard; Worrell, Gregory A; Berry, Brent M; Inman, Cory; Lin, Jui-Jui; Davis, Kathryn A; Das, Sandhitsu R; Stein, Joel M; Jobst, Barbara C; Zaghloul, Kareem A; Sheth, Sameer A; Rizzuto, Daniel S; Kahana, Michael J

2017-07-15

Neural networks that span the medial temporal lobe (MTL), prefrontal cortex, and posterior cortical regions are essential to episodic memory function in humans. Encoding and retrieval are supported by the engagement of both distinct neural pathways across the cortex and common structures within the medial temporal lobes. However, the degree to which memory performance can be determined by neural processing that is common to encoding and retrieval remains to be determined. To identify neural signatures of successful memory function, we administered a delayed free-recall task to 187 neurosurgical patients implanted with subdural or intraparenchymal depth electrodes. We developed multivariate classifiers to identify patterns of spectral power across the brain that independently predicted successful episodic encoding and retrieval. During encoding and retrieval, patterns of increased high frequency activity in prefrontal, MTL, and inferior parietal cortices, accompanied by widespread decreases in low frequency power across the brain predicted successful memory function. Using a cross-decoding approach, we demonstrate the ability to predict memory function across distinct phases of the free-recall task. Furthermore, we demonstrate that classifiers that combine information from both encoding and retrieval states can outperform task-independent models. These findings suggest that the engagement of a core memory network during either encoding or retrieval shapes the ability to remember the past, despite distinct neural interactions that facilitate encoding and retrieval. Copyright © 2017 Elsevier Inc. All rights reserved.

Recursive Neural Networks Based on PSO for Image Parsing

Directory of Open Access Journals (Sweden)

Guo-Rong Cai

2013-01-01

Full Text Available This paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO and Recursive Neural Networks (RNNs. State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause problems due to the nondifferentiable objective function. In order to solve this problem, the PSO algorithm has been employed to tune the weights of RNN for minimizing the objective. Experimental results obtained on the Stanford background dataset show that our PSO-based training algorithm outperforms traditional RNN, Pixel CRF, region-based energy, simultaneous MRF, and superpixel MRF.

Horizontal ichthyoplankton tow-net system with unobstructed net opening

Science.gov (United States)

Nester, Robert T.

1987-01-01

The larval fish sampler described here consists of a modified bridle, frame, and net system with an obstruction-free net opening and is small enough for use on boats 10 m or less in length. The tow net features a square net frame attached to a 0.5-m-diameter cylinder-on-cone plankton net with a bridle designed to eliminate all obstructions forward of the net opening, significantly reducing currents and vibrations in the water directly preceding the net. This system was effective in collecting larvae representing more than 25 species of fish at sampling depths ranging from surface to 10 m and could easily be used at greater depths.

Using Outperformance Pay to Motivate Academics: Insiders' Accounts of Promises and Problems

Science.gov (United States)

Field, Laurie

2015-01-01

Many researchers have investigated the appropriateness of pay for outperformance, (also called "merit-based pay" and "performance-based pay") for academics, but a review of this body of work shows that the voice of academics themselves is largely absent. This article is a contribution to addressing this gap, summarising the…

Higher-moment measurements of net-kaon, net-charge and net-proton multiplicity distributions at STAR

International Nuclear Information System (INIS)

Sarkar, Amal

2014-01-01

In this paper, we report the measurements of the various moments, such as mean, standard deviation (σ), skewness (S) and kurtosis (κ) of the net-kaon, net-charge and net-proton multiplicity distributions at mid-rapidity in Au + Au collisions from √(s NN )=7.7 to 200 GeV with the STAR experiment at RHIC. This work has been done with the aim to locate the critical point on the QCD phase diagram. These moments and their products are related to the thermodynamic susceptibilities of conserved quantities such as net baryon number, net charge, and net strangeness as well as to the correlation length of the system which diverges in an ideal infinite thermodynamic system at the critical point. For a finite system, existing for a finite time, a non-monotonic behavior of these variables would indicate the presence of the critical point. Furthermore, we also present the moment products Sσ, κσ 2 of net-kaon, net-charge and net-proton multiplicity distributions as a function of collision centrality and energy. The energy and the centrality dependence of higher moments and their products have been compared with different models

A Timed Colored Petri Net Simulation-Based Self-Adaptive Collaboration Method for Production-Logistics Systems

Directory of Open Access Journals (Sweden)

Zhengang Guo

2017-03-01

Full Text Available Complex and customized manufacturing requires a high level of collaboration between production and logistics in a flexible production system. With the widespread use of Internet of Things technology in manufacturing, a great amount of real-time and multi-source manufacturing data and logistics data is created, that can be used to perform production-logistics collaboration. To solve the aforementioned problems, this paper proposes a timed colored Petri net simulation-based self-adaptive collaboration method for Internet of Things-enabled production-logistics systems. The method combines the schedule of token sequences in the timed colored Petri net with real-time status of key production and logistics equipment. The key equipment is made ‘smart’ to actively publish or request logistics tasks. An integrated framework based on a cloud service platform is introduced to provide the basis for self-adaptive collaboration of production-logistics systems. A simulation experiment is conducted by using colored Petri nets (CPN Tools to validate the performance and applicability of the proposed method. Computational experiments demonstrate that the proposed method outperforms the event-driven method in terms of reductions of waiting time, makespan, and electricity consumption. This proposed method is also applicable to other manufacturing systems to implement production-logistics collaboration.

Adaptive Learning Rule for Hardware-based Deep Neural Networks Using Electronic Synapse Devices

OpenAIRE

Lim, Suhwan; Bae, Jong-Ho; Eum, Jai-Ho; Lee, Sungtae; Kim, Chul-Heung; Kwon, Dongseok; Park, Byung-Gook; Lee, Jong-Ho

2017-01-01

In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance characteristics. This adaptive learning rule, which enables forward, backward propagation, as well as weight updates in hardware, is helpful during the implementation of power-efficient and high-speed deep neural networks. In simulations using a three-layer perceptron net...

Gas Classification Using Deep Convolutional Neural Networks

Science.gov (United States)

Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

2018-01-01

In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP). PMID:29316723

Gas Classification Using Deep Convolutional Neural Networks.

Science.gov (United States)

Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

2018-01-08

In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

Feature to prototype transition in neural networks

Science.gov (United States)

Krotov, Dmitry; Hopfield, John

Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.

PREDICTION OF DEMAND FOR PRIMARY BOND OFFERINGS USING ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Michal Tkac

2014-12-01

Full Text Available Purpose: Primary bond markets represent an interesting investment opportunity not only for banks, insurance companies, and other institutional investors, but also for individuals looking for capital gains. Since offered securities vary in terms of their rating, industrial classification, coupon, or maturity, demand of buyers for particular offerings often overcomes issued volume and price of given bond on secondary market consequently rises. Investors might be regarded as consumers purchasing required service according to their specific preferences at desired price. This paper aims at analysis of demand for bonds on primary market using artificial neural networks.Design/methodology: We design a multilayered feedforward neural network trained by Levenberg-Marquardt algorithm in order to estimate demand for individual bonds based on parameters of particular offerings. Outcomes obtained by artificial neural network are compared with conventional econometric methods.Findings: Our results indicate that artificial neural network significantly outperformed standard econometric techniques and on examined sample of primary bond offerings achieved considerably better performance in terms of prediction accuracy and mean squared error.Originality: We show that proposed neural network is able to successfully predict demand for primary obligation offerings based on their specifications. Moreover, we identify relevant parameters of issues which are able to considerably affect total demand for given security.  Our findings might not only help investors to detect marketable securities, but also enable issuing entities to increase demand for their bonds in order to decrease their offering price. 

Optical implementation of a feature-based neural network with application to automatic target recognition

Science.gov (United States)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

Application of artificial neural networks in particle physics

International Nuclear Information System (INIS)

Kolanoski, H.

1995-04-01

The application of Artificial Neural Networks in Particle Physics is reviewed. Most common is the use of feed-forward nets for event classification and function approximation. This network type is best suited for a hardware implementation and special VLSI chips are available which are used in fast trigger processors. Also discussed are fully connected networks of the Hopfield type for pattern recognition in tracking detectors. (orig.)

Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image.

Science.gov (United States)

Xu, Kele; Feng, Dawei; Mi, Haibo

2017-11-23

The automatic detection of diabetic retinopathy is of vital importance, as it is the main cause of irreversible vision loss in the working-age population in the developed world. The early detection of diabetic retinopathy occurrence can be very helpful for clinical treatment; although several different feature extraction approaches have been proposed, the classification task for retinal images is still tedious even for those trained clinicians. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. Thus, in this paper, we explored the use of deep convolutional neural network methodology for the automatic classification of diabetic retinopathy using color fundus image, and obtained an accuracy of 94.5% on our dataset, outperforming the results obtained by using classical approaches.

T-wave end detection using neural networks and Support Vector Machines.

Science.gov (United States)

Suárez-León, Alexander Alexeis; Varon, Carolina; Willems, Rik; Van Huffel, Sabine; Vázquez-Seisdedos, Carlos Román

2018-05-01

In this paper we propose a new approach for detecting the end of the T-wave in the electrocardiogram (ECG) using Neural Networks and Support Vector Machines. Both, Multilayer Perceptron (MLP) neural networks and Fixed-Size Least-Squares Support Vector Machines (FS-LSSVM) were used as regression algorithms to determine the end of the T-wave. Different strategies for selecting the training set such as random selection, k-means, robust clustering and maximum quadratic (Rényi) entropy were evaluated. Individual parameters were tuned for each method during training and the results are given for the evaluation set. A comparison between MLP and FS-LSSVM approaches was performed. Finally, a fair comparison of the FS-LSSVM method with other state-of-the-art algorithms for detecting the end of the T-wave was included. The experimental results show that FS-LSSVM approaches are more suitable as regression algorithms than MLP neural networks. Despite the small training sets used, the FS-LSSVM methods outperformed the state-of-the-art techniques. FS-LSSVM can be successfully used as a T-wave end detection algorithm in ECG even with small training set sizes. Copyright © 2018 Elsevier Ltd. All rights reserved.

Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors

Directory of Open Access Journals (Sweden)

Fernando Moya Rueda

2018-05-01

Full Text Available Human activity recognition (HAR is a classification task for recognizing human movements. Methods of HAR are of great interest as they have become tools for measuring occurrences and durations of human actions, which are the basis of smart assistive technologies and manual processes analysis. Recently, deep neural networks have been deployed for HAR in the context of activities of daily living using multichannel time-series. These time-series are acquired from body-worn devices, which are composed of different types of sensors. The deep architectures process these measurements for finding basic and complex features in human corporal movements, and for classifying them into a set of human actions. As the devices are worn at different parts of the human body, we propose a novel deep neural network for HAR. This network handles sequence measurements from different body-worn devices separately. An evaluation of the architecture is performed on three datasets, the Oportunity, Pamap2, and an industrial dataset, outperforming the state-of-the-art. In addition, different network configurations will also be evaluated. We find that applying convolutions per sensor channel and per body-worn device improves the capabilities of convolutional neural network (CNNs.

High level cognitive information processing in neural networks

Science.gov (United States)

Barnden, John A.; Fields, Christopher A.

1992-01-01

Two related research efforts were addressed: (1) high-level connectionist cognitive modeling; and (2) local neural circuit modeling. The goals of the first effort were to develop connectionist models of high-level cognitive processes such as problem solving or natural language understanding, and to understand the computational requirements of such models. The goals of the second effort were to develop biologically-realistic model of local neural circuits, and to understand the computational behavior of such models. In keeping with the nature of NASA's Innovative Research Program, all the work conducted under the grant was highly innovative. For instance, the following ideas, all summarized, are contributions to the study of connectionist/neural networks: (1) the temporal-winner-take-all, relative-position encoding, and pattern-similarity association techniques; (2) the importation of logical combinators into connection; (3) the use of analogy-based reasoning as a bridge across the gap between the traditional symbolic paradigm and the connectionist paradigm; and (4) the application of connectionism to the domain of belief representation/reasoning. The work on local neural circuit modeling also departs significantly from the work of related researchers. In particular, its concentration on low-level neural phenomena that could support high-level cognitive processing is unusual within the area of biological local circuit modeling, and also serves to expand the horizons of the artificial neural net field.

Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

Directory of Open Access Journals (Sweden)

Svitlana Volkova

, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e Location-specific models outperform previously used location-independent models e.g., U.S. only. (f Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets.

Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

Science.gov (United States)

Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D

2017-01-01

social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets.

Identification of Complex Dynamical Systems with Neural Networks (2/2)

CERN Multimedia

CERN. Geneva

2016-01-01

The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...

Identification of Complex Dynamical Systems with Neural Networks (1/2)

CERN Multimedia

CERN. Geneva

2016-01-01

The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...

An intelligent sales forecasting system through integration of artificial neural networks and fuzzy neural networks with fuzzy weight elimination.

Science.gov (United States)

Kuo, R J; Wu, P; Wang, C P

2002-09-01

Sales forecasting plays a very prominent role in business strategy. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average (ARMA). However, sales forecasting is very complicated owing to influence by internal and external environments. Recently, artificial neural networks (ANNs) have also been applied in sales forecasting since their promising performances in the areas of control and pattern recognition. However, further improvement is still necessary since unique circumstances, e.g. promotion, cause a sudden change in the sales pattern. Thus, this study utilizes a proposed fuzzy neural network (FNN), which is able to eliminate the unimportant weights, for the sake of learning fuzzy IF-THEN rules obtained from the marketing experts with respect to promotion. The result from FNN is further integrated with the time series data through an ANN. Both the simulated and real-world problem results show that FNN with weight elimination can have lower training error compared with the regular FNN. Besides, real-world problem results also indicate that the proposed estimation system outperforms the conventional statistical method and single ANN in accuracy.

Axial design of fuel for BWRs using neural networks

International Nuclear Information System (INIS)

Ortiz, J.J.; Castillo, A.; Montes, J.L.; Perusquia, R.

2007-01-01

In this work a new system of axial optimization of fuel is presented based on a recurrent multi state neural net called RENODC. They are described with detail the main characteristics of this type of neural net (architecture, energy function and actualization of neural states) and like was adapted to the assemble design of nuclear fuel. The fuel design is proven by means of a fuel recharge and pre determined control rod patterns. By this way a good axial fuel design one has, when the thermal limits are fulfilled along the cycle, the reactor stays critic and at least the wanted longitude of the cycle is reached; also the margin of in cold turned off is verified. The assemble of fuel created with RENODC it is substituted by a recharge assemble and it is sought to verify that the energy requirements and aspects of safety are completed. The used cycle corresponds to a balance cycle of 18 months that it can be applied to the Laguna Verde Nucleo electric Central. The tests demonstrate the effectiveness of the system to reach satisfactory results in times of CPU of around 4 hours. This way, it could be proven that the design proposed with a lightly superior enrichment to that of the substituted design, fulfills the energy requirements. In later stages of this project this system will be coupled to the other optimization modules that are already had. (Author)

Comparing various artificial neural network types for water temperature prediction in rivers

Science.gov (United States)

Piotrowski, Adam P.; Napiorkowski, Maciej J.; Napiorkowski, Jaroslaw J.; Osuch, Marzena

2015-10-01

A number of methods have been proposed for the prediction of streamwater temperature based on various meteorological and hydrological variables. The present study shows a comparison of few types of data-driven neural networks (multi-layer perceptron, product-units, adaptive-network-based fuzzy inference systems and wavelet neural networks) and nearest neighbour approach for short time streamwater temperature predictions in two natural catchments (mountainous and lowland) located in temperate climate zone, with snowy winters and hot summers. To allow wide applicability of such models, autoregressive inputs are not used and only easily available measurements are considered. Each neural network type is calibrated independently 100 times and the mean, median and standard deviation of the results are used for the comparison. Finally, the ensemble aggregation approach is tested. The results show that simple and popular multi-layer perceptron neural networks are in most cases not outperformed by more complex and advanced models. The choice of neural network is dependent on the way the models are compared. This may be a warning for anyone who wish to promote own models, that their superiority should be verified in different ways. The best results are obtained when mean, maximum and minimum daily air temperatures from the previous days are used as inputs, together with the current runoff and declination of the Sun from two recent days. The ensemble aggregation approach allows reducing the mean square error up to several percent, depending on the case, and noticeably diminishes differences in modelling performance obtained by various neural network types.

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

Energy Technology Data Exchange (ETDEWEB)

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solis Sanches, L. O.; Miranda, R. Castaneda; Cervantes Viramontes, J. M. [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica. Av. Ramon Lopez Velarde 801. Col. Centro Zacatecas, Zac (Mexico); Vega-Carrillo, H. R. [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica. Av. Ramon Lopez Velarde 801. Col. Centro Zacatecas, Zac., Mexico. and Unidad Academica de Estudios Nucleares. C. Cip (Mexico)

2013-07-03

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called ''Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres'', (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the ''Robust design of artificial neural networks methodology'' and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored at synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of {sup 252}Cf, {sup 241}AmBe and {sup 239}PuBe neutron sources measured with a Bonner spheres system.

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

International Nuclear Information System (INIS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-01-01

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called ''Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres'', (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the ''Robust design of artificial neural networks methodology'' and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored at synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of 252 Cf, 241 AmBe and 239 PuBe neutron sources measured with a Bonner spheres system

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

Science.gov (United States)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called "Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres", (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the "Robust design of artificial neural networks methodology" and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored at synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of 252Cf, 241AmBe and 239PuBe neutron sources measured with a Bonner spheres system.

Classification of polycystic ovary based on ultrasound images using competitive neural network

Science.gov (United States)

Dewi, R. M.; Adiwijaya; Wisesty, U. N.; Jondri

2018-03-01

Infertility in the women reproduction system due to inhibition of follicles maturation process causing the number of follicles which is called polycystic ovaries (PCO). PCO detection is still operated manually by a gynecologist by counting the number and size of follicles in the ovaries, so it takes a long time and needs high accuracy. In general, PCO can be detected by calculating stereology or feature extraction and classification. In this paper, we designed a system to classify PCO by using the feature extraction (Gabor Wavelet method) and Competitive Neural Network (CNN). CNN was selected because this method is the combination between Hemming Net and The Max Net so that the data classification can be performed based on the specific characteristics of ultrasound data. Based on the result of system testing, Competitive Neural Network obtained the highest accuracy is 80.84% and the time process is 60.64 seconds (when using 32 feature vectors as well as weight and bias values respectively of 0.03 and 0.002).

Character-level neural network for biomedical named entity recognition.

Science.gov (United States)

Gridach, Mourad

2017-06-01

Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of feature engineering, lexicons and data pre-processing to achieve high performance. In this paper, we introduce a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks. We evaluate our system on two datasets: JNLPBA corpus and the BioCreAtIvE II Gene Mention (GM) corpus. We obtained state-of-the-art performance by outperforming the previous systems. To the best of our knowledge, we are the first to investigate the combination of deep neural networks, CRF, word embeddings and character-level representation in recognizing biomedical named entities. Copyright © 2017 Elsevier Inc. All rights reserved.

Effective Multifocus Image Fusion Based on HVS and BP Neural Network

Directory of Open Access Journals (Sweden)

Yong Yang

2014-01-01

Full Text Available The aim of multifocus image fusion is to fuse the images taken from the same scene with different focuses to obtain a resultant image with all objects in focus. In this paper, a novel multifocus image fusion method based on human visual system (HVS and back propagation (BP neural network is presented. Three features which reflect the clarity of a pixel are firstly extracted and used to train a BP neural network to determine which pixel is clearer. The clearer pixels are then used to construct the initial fused image. Thirdly, the focused regions are detected by measuring the similarity between the source images and the initial fused image followed by morphological opening and closing operations. Finally, the final fused image is obtained by a fusion rule for those focused regions. Experimental results show that the proposed method can provide better performance and outperform several existing popular fusion methods in terms of both objective and subjective evaluations.

Net-baryon-, net-proton-, and net-charge kurtosis in heavy-ion collisions within a relativistic transport approach

International Nuclear Information System (INIS)

Nahrgang, Marlene; Schuster, Tim; Stock, Reinhard; Mitrovski, Michael; Bleicher, Marcus

2012-01-01

We explore the potential of net-baryon, net-proton and net-charge kurtosis measurements to investigate the properties of hot and dense matter created in relativistic heavy-ion collisions. Contrary to calculations in a grand-canonical ensemble we explicitly take into account exact electric and baryon charge conservation on an event-by-event basis. This drastically limits the width of baryon fluctuations. A simple model to account for this is to assume a grand-canonical distribution with a sharp cut-off at the tails. We present baseline predictions of the energy dependence of the net-baryon, net-proton and net-charge kurtosis for central (b≤2.75 fm) Pb+Pb/Au+Au collisions from E lab =2A GeV to √(s NN )=200 GeV from the UrQMD model. While the net-charge kurtosis is compatible with values around zero, the net-baryon number decreases to large negative values with decreasing beam energy. The net-proton kurtosis becomes only slightly negative for low √(s NN ). (orig.)

Neural representations of emotion are organized around abstract event features.

Science.gov (United States)

Skerry, Amy E; Saxe, Rebecca

2015-08-03

Research on emotion attribution has tended to focus on the perception of overt expressions of at most five or six basic emotions. However, our ability to identify others' emotional states is not limited to perception of these canonical expressions. Instead, we make fine-grained inferences about what others feel based on the situations they encounter, relying on knowledge of the eliciting conditions for different emotions. In the present research, we provide convergent behavioral and neural evidence concerning the representations underlying these concepts. First, we find that patterns of activity in mentalizing regions contain information about subtle emotional distinctions conveyed through verbal descriptions of eliciting situations. Second, we identify a space of abstract situation features that well captures the emotion discriminations subjects make behaviorally and show that this feature space outperforms competing models in capturing the similarity space of neural patterns in these regions. Together, the data suggest that our knowledge of others' emotions is abstract and high dimensional, that brain regions selective for mental state reasoning support relatively subtle distinctions between emotion concepts, and that the neural representations in these regions are not reducible to more primitive affective dimensions such as valence and arousal. Copyright © 2015 Elsevier Ltd. All rights reserved.

Fast neural-net based fake track rejection in the LHCb reconstruction

CERN Document Server

De Cian, Michel; Seyfert, Paul; Stahl, Sascha

2017-01-01

A neural-network based algorithm to identify fake tracks in the LHCb pattern recognition is presented. This algorithm, called ghost probability, retains more than 99 % of well reconstructed tracks while reducing the number of fake tracks by 60 %. It is fast enough to fit into the CPU time budget of the software trigger farm and thus reduces the combinatorics of the decay reconstructions, as well as the number of tracks that need to be processed by the particle identification algorithms. As a result, it strongly contributes to the achievement of having the same reconstruction online and offline in the LHCb experiment in Run II of the LHC.

A neural network approach to job-shop scheduling.

Science.gov (United States)

Zhou, D N; Cherkassky, V; Baldwin, T R; Olson, D E

1991-01-01

A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity.

Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging.

Science.gov (United States)

Mohseni Salehi, Seyed Sadegh; Erdogmus, Deniz; Gholipour, Ali

2017-11-01

Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and the robustness of brain extraction, therefore, are crucial for the accuracy of the entire brain analysis process. The state-of-the-art brain extraction techniques rely heavily on the accuracy of alignment or registration between brain atlases and query brain anatomy, and/or make assumptions about the image geometry, and therefore have limited success when these assumptions do not hold or image registration fails. With the aim of designing an accurate, learning-based, geometry-independent, and registration-free brain extraction tool, in this paper, we present a technique based on an auto-context convolutional neural network (CNN), in which intrinsic local and global image features are learned through 2-D patches of different window sizes. We consider two different architectures: 1) a voxelwise approach based on three parallel 2-D convolutional pathways for three different directions (axial, coronal, and sagittal) that implicitly learn 3-D image information without the need for computationally expensive 3-D convolutions and 2) a fully convolutional network based on the U-net architecture. Posterior probability maps generated by the networks are used iteratively as context information along with the original image patches to learn the local shape and connectedness of the brain to extract it from non-brain tissue. The brain extraction results we have obtained from our CNNs are superior to the recently reported results in the literature on two publicly available benchmark data sets, namely, LPBA40 and OASIS, in which we obtained the Dice overlap coefficients of 97.73% and 97.62%, respectively. Significant improvement was achieved via our auto-context algorithm. Furthermore, we evaluated the performance of our algorithm in the challenging problem of extracting arbitrarily oriented fetal brains in reconstructed fetal brain magnetic

An improved genetic algorithm for designing optimal temporal patterns of neural stimulation

Science.gov (United States)

Cassar, Isaac R.; Titus, Nathan D.; Grill, Warren M.

2017-12-01

Objective. Electrical neuromodulation therapies typically apply constant frequency stimulation, but non-regular temporal patterns of stimulation may be more effective and more efficient. However, the design space for temporal patterns is exceedingly large, and model-based optimization is required for pattern design. We designed and implemented a modified genetic algorithm (GA) intended for design optimal temporal patterns of electrical neuromodulation. Approach. We tested and modified standard GA methods for application to designing temporal patterns of neural stimulation. We evaluated each modification individually and all modifications collectively by comparing performance to the standard GA across three test functions and two biophysically-based models of neural stimulation. Main results. The proposed modifications of the GA significantly improved performance across the test functions and performed best when all were used collectively. The standard GA found patterns that outperformed fixed-frequency, clinically-standard patterns in biophysically-based models of neural stimulation, but the modified GA, in many fewer iterations, consistently converged to higher-scoring, non-regular patterns of stimulation. Significance. The proposed improvements to standard GA methodology reduced the number of iterations required for convergence and identified superior solutions.

Neural network segmentation of magnetic resonance images

International Nuclear Information System (INIS)

Frederick, B.

1990-01-01

Neural networks are well adapted to the task of grouping input patterns into subsets which share some similarity. Moreover, once trained, they can generalize their classification rules to classify new data sets. Sets of pixel intensities from magnetic resonance (MR) images provide a natural input to a neural network; by varying imaging parameters, MR images can reflect various independent physical parameters of tissues in their pixel intensities. A neural net can then be trained to classify physically similar tissue types based on sets of pixel intensities resulting from different imaging studies on the same subject. This paper reports that a neural network classifier for image segmentation was implanted on a Sun 4/60, and was tested on the task of classifying tissues of canine head MR images. Four images of a transaxial slice with different imaging sequences were taken as input to the network (three spin-echo images and an inversion recovery image). The training set consisted of 691 representative samples of gray matter, white matter, cerebrospinal fluid, bone, and muscle preclassified by a neuroscientist. The network was trained using a fast backpropagation algorithm to derive the decision criteria to classify any location in the image by its pixel intensities, and the image was subsequently segmented by the classifier

Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam

Directory of Open Access Journals (Sweden)

A. El-Shafie

2011-03-01

Full Text Available Artificial neural networks (ANN have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces problems. One of the major shortcomings is the search for the optimal input pattern in order to enhance the forecasting capabilities for the output. The second challenge is the over-fitting problem during the training procedure and this occurs when ANN loses its generalization. In this research, autocorrelation and cross correlation analyses are suggested as a method for searching the optimal input pattern. On the other hand, two generalized methods namely, Regularized Neural Network (RNN and Ensemble Neural Network (ENN models are developed to overcome the drawbacks of classical ANN models. Using Generalized Neural Network (GNN helped avoid over-fitting of training data which was observed as a limitation of classical ANN models. Real inflow data collected over the last 130 years at Lake Nasser was used to train, test and validate the proposed model. Results show that the proposed GNN model outperforms non-generalized neural network and conventional auto-regressive models and it could provide accurate inflow forecasting.

Petri Nets

Indian Academy of Sciences (India)

In a computer system, for example, typical discrete events ... This project brought out a series of influential reports on Petri net theory in the mid and late ... Technology became a leading centre for Petri net research and from then on, Petri nets ...

Fine-grained vehicle type recognition based on deep convolution neural networks

Directory of Open Access Journals (Sweden)

Hongcai CHEN

2017-12-01

Full Text Available Public security and traffic department put forward higher requirements for real-time performance and accuracy of vehicle type recognition in complex traffic scenes. Aiming at the problems of great plice forces occupation, low retrieval efficiency, and lacking of intelligence for dealing with false license, fake plate vehicles and vehicles without plates, this paper proposes a vehicle type fine-grained recognition method based GoogleNet deep convolution neural networks. The filter size and numbers of convolution neural network are designed, the activation function and vehicle type classifier are optimally selected, and a new network framework is constructed for vehicle type fine-grained recognition. The experimental results show that the proposed method has 97% accuracy for vehicle type fine-grained recognition and has greater improvement than the original GoogleNet model. Moreover, the new model effectively reduces the number of training parameters, and saves computer memory. Fine-grained vehicle type recognition can be used in intelligent traffic management area, and has important theoretical research value and practical significance.

Neural network control of focal position during time-lapse microscopy of cells.

Science.gov (United States)

Wei, Ling; Roberts, Elijah

2018-05-09

Live-cell microscopy is quickly becoming an indispensable technique for studying the dynamics of cellular processes. Maintaining the specimen in focus during image acquisition is crucial for high-throughput applications, especially for long experiments or when a large sample is being continuously scanned. Automated focus control methods are often expensive, imperfect, or ill-adapted to a specific application and are a bottleneck for widespread adoption of high-throughput, live-cell imaging. Here, we demonstrate a neural network approach for automatically maintaining focus during bright-field microscopy. Z-stacks of yeast cells growing in a microfluidic device were collected and used to train a convolutional neural network to classify images according to their z-position. We studied the effect on prediction accuracy of the various hyperparameters of the neural network, including downsampling, batch size, and z-bin resolution. The network was able to predict the z-position of an image with ±1 μm accuracy, outperforming human annotators. Finally, we used our neural network to control microscope focus in real-time during a 24 hour growth experiment. The method robustly maintained the correct focal position compensating for 40 μm of focal drift and was insensitive to changes in the field of view. About ~100 annotated z-stacks were required to train the network making our method quite practical for custom autofocus applications.

Semantic Segmentation of Convolutional Neural Network for Supervised Classification of Multispectral Remote Sensing

Science.gov (United States)

Xue, L.; Liu, C.; Wu, Y.; Li, H.

2018-04-01

Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.

High-Performance Neural Networks for Visual Object Classification

OpenAIRE

Cireşan, Dan C.; Meier, Ueli; Masci, Jonathan; Gambardella, Luca M.; Schmidhuber, Jürgen

2011-01-01

We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better ...

Nonlinear System Identification Using Neural Networks Trained with Natural Gradient Descent

Directory of Open Access Journals (Sweden)

Ibnkahla Mohamed

2003-01-01

Full Text Available We use natural gradient (NG learning neural networks (NNs for modeling and identifying nonlinear systems with memory. The nonlinear system is comprised of a discrete-time linear filter followed by a zero-memory nonlinearity . The NN model is composed of a linear adaptive filter followed by a two-layer memoryless nonlinear NN. A Kalman filter-based technique and a search-and-converge method have been employed for the NG algorithm. It is shown that the NG descent learning significantly outperforms the ordinary gradient descent and the Levenberg-Marquardt (LM procedure in terms of convergence speed and mean squared error (MSE performance.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

Science.gov (United States)

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

The equivalency between logic Petri workflow nets and workflow nets.

Science.gov (United States)

Wang, Jing; Yu, ShuXia; Du, YuYue

2015-01-01

Logic Petri nets (LPNs) can describe and analyze batch processing functions and passing value indeterminacy in cooperative systems. Logic Petri workflow nets (LPWNs) are proposed based on LPNs in this paper. Process mining is regarded as an important bridge between modeling and analysis of data mining and business process. Workflow nets (WF-nets) are the extension to Petri nets (PNs), and have successfully been used to process mining. Some shortcomings cannot be avoided in process mining, such as duplicate tasks, invisible tasks, and the noise of logs. The online shop in electronic commerce in this paper is modeled to prove the equivalence between LPWNs and WF-nets, and advantages of LPWNs are presented.

The Equivalency between Logic Petri Workflow Nets and Workflow Nets

Science.gov (United States)

Wang, Jing; Yu, ShuXia; Du, YuYue

2015-01-01

Logic Petri nets (LPNs) can describe and analyze batch processing functions and passing value indeterminacy in cooperative systems. Logic Petri workflow nets (LPWNs) are proposed based on LPNs in this paper. Process mining is regarded as an important bridge between modeling and analysis of data mining and business process. Workflow nets (WF-nets) are the extension to Petri nets (PNs), and have successfully been used to process mining. Some shortcomings cannot be avoided in process mining, such as duplicate tasks, invisible tasks, and the noise of logs. The online shop in electronic commerce in this paper is modeled to prove the equivalence between LPWNs and WF-nets, and advantages of LPWNs are presented. PMID:25821845

Adolescent development of context-dependent stimulus-reward association memory and its neural correlates.

Science.gov (United States)

Voss, Joel L; O'Neil, Jonathan T; Kharitonova, Maria; Briggs-Gowan, Margaret J; Wakschlag, Lauren S

2015-01-01

Expression of learned stimulus-reward associations based on context is essential for regulation of behavior to meet situational demands. Contextual regulation improves during development, although the developmental progression of relevant neural and cognitive processes is not fully specified. We therefore measured neural correlates of flexible, contextual expression of stimulus-reward associations in pre/early-adolescent children (ages 9-13 years) and young adults (ages 19-22 years). After reinforcement learning using standard parameters, a contextual reversal manipulation was used whereby contextual cues indicated that stimulus-reward associations were the same as previously reinforced for some trials (consistent trials) or were reversed on other trials (inconsistent trials). Subjects were thus required to respond according to original stimulus-reward associations vs. reversed associations based on trial-specific contextual cues. Children and young adults did not differ in reinforcement learning or in relevant functional magnetic resonance imaging (fMRI) correlates. In contrast, adults outperformed children during contextual reversal, with better performance specifically for inconsistent trials. fMRI signals corresponding to this selective advantage included greater activity in lateral prefrontal cortex (LPFC), hippocampus, and dorsal striatum for young adults relative to children. Flexible expression of stimulus-reward associations based on context thus improves via adolescent development, as does recruitment of brain regions involved in reward learning and contextual expression of memory. HighlightsEarly-adolescent children and young adults were equivalent in reinforcement learning.Adults outperformed children in contextual expression of stimulus-reward associations.Adult advantages correlated with increased activity of relevant brain regions.Specific neurocognitive developmental changes support better contextual regulation.

SupportNet: a novel incremental learning framework through deep learning and support data

KAUST Repository

Li, Yu; Li, Zhongxiao; Ding, Lizhong; Hu, Yuhui; Chen, Wei; Gao, Xin

2018-01-01

Motivation: In most biological data sets, the amount of data is regularly growing and the number of classes is continuously increasing. To deal with the new data from the new classes, one approach is to train a classification model, e.g., a deep learning model, from scratch based on both old and new data. This approach is highly computationally costly and the extracted features are likely very different from the ones extracted by the model trained on the old data alone, which leads to poor model robustness. Another approach is to fine tune the trained model from the old data on the new data. However, this approach often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as the catastrophic forgetting problem. To our knowledge, this problem has not been studied in the field of bioinformatics despite its existence in many bioinformatic problems. Results: Here we propose a novel method, SupportNet, to solve the catastrophic forgetting problem efficiently and effectively. SupportNet combines the strength of deep learning and support vector machine (SVM), where SVM is used to identify the support data from the old data, which are fed to the deep learning model together with the new data for further training so that the model can review the essential information of the old data when learning the new information. Two powerful consolidation regularizers are applied to ensure the robustness of the learned model. Comprehensive experiments on various tasks, including enzyme function prediction, subcellular structure classification and breast tumor classification, show that SupportNet drastically outperforms the state-of-the-art incremental learning methods and reaches similar performance as the deep learning model trained from scratch on both old and new data. Availability: Our program is accessible at: \\url{https://github.com/lykaust15/SupportNet}.

SupportNet: a novel incremental learning framework through deep learning and support data

KAUST Repository

Li, Yu

2018-05-08

Motivation: In most biological data sets, the amount of data is regularly growing and the number of classes is continuously increasing. To deal with the new data from the new classes, one approach is to train a classification model, e.g., a deep learning model, from scratch based on both old and new data. This approach is highly computationally costly and the extracted features are likely very different from the ones extracted by the model trained on the old data alone, which leads to poor model robustness. Another approach is to fine tune the trained model from the old data on the new data. However, this approach often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as the catastrophic forgetting problem. To our knowledge, this problem has not been studied in the field of bioinformatics despite its existence in many bioinformatic problems. Results: Here we propose a novel method, SupportNet, to solve the catastrophic forgetting problem efficiently and effectively. SupportNet combines the strength of deep learning and support vector machine (SVM), where SVM is used to identify the support data from the old data, which are fed to the deep learning model together with the new data for further training so that the model can review the essential information of the old data when learning the new information. Two powerful consolidation regularizers are applied to ensure the robustness of the learned model. Comprehensive experiments on various tasks, including enzyme function prediction, subcellular structure classification and breast tumor classification, show that SupportNet drastically outperforms the state-of-the-art incremental learning methods and reaches similar performance as the deep learning model trained from scratch on both old and new data. Availability: Our program is accessible at: \\\\url{https://github.com/lykaust15/SupportNet}.

Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks.

Science.gov (United States)

Wolterink, Jelmer M; Leiner, Tim; de Vos, Bob D; van Hamersvelt, Robbert W; Viergever, Max A; Išgum, Ivana

2016-12-01

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. CAC is clinically quantified in cardiac calcium scoring CT (CSCT), but it has been shown that cardiac CT angiography (CCTA) may also be used for this purpose. We present a method for automatic CAC quantification in CCTA. This method uses supervised learning to directly identify and quantify CAC without a need for coronary artery extraction commonly used in existing methods. The study included cardiac CT exams of 250 patients for whom both a CCTA and a CSCT scan were available. To restrict the volume-of-interest for analysis, a bounding box around the heart is automatically determined. The bounding box detection algorithm employs a combination of three ConvNets, where each detects the heart in a different orthogonal plane (axial, sagittal, coronal). These ConvNets were trained using 50 cardiac CT exams. In the remaining 200 exams, a reference standard for CAC was defined in CSCT and CCTA. Out of these, 100 CCTA scans were used for training, and the remaining 100 for evaluation of a voxel classification method for CAC identification. The method uses ConvPairs, pairs of convolutional neural networks (ConvNets). The first ConvNet in a pair identifies voxels likely to be CAC, thereby discarding the majority of non-CAC-like voxels such as lung and fatty tissue. The identified CAC-like voxels are further classified by the second ConvNet in the pair, which distinguishes between CAC and CAC-like negatives. Given the different task of each ConvNet, they share their architecture, but not their weights. Input patches are either 2.5D or 3D. The ConvNets are purely convolutional, i.e. no pooling layers are present and fully connected layers are implemented as convolutions, thereby allowing efficient voxel classification. The performance of individual 2.5D and 3D ConvPairs with input sizes of 15 and 25 voxels, as well as the performance of ensembles of these Conv

Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

Science.gov (United States)

Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

2017-01-01

Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

Modelling and Forecasting Cruise Tourism Demand to İzmir by Different Artificial Neural Network Architectures

Directory of Open Access Journals (Sweden)

Murat Cuhadar

2014-03-01

Full Text Available Abstract Cruise ports emerged as an important sector for the economy of Turkey bordered on three sides by water. Forecasting cruise tourism demand ensures better planning, efficient preparation at the destination and it is the basis for elaboration of future plans. In the recent years, new techniques such as; artificial neural networks were employed for developing of the predictive models to estimate tourism demand. In this study, it is aimed to determine the forecasting method that provides the best performance when compared the forecast accuracy of Multi-layer Perceptron (MLP, Radial Basis Function (RBF and Generalized Regression neural network (GRNN to estimate the monthly inbound cruise tourism demand to İzmir via the method giving best results. We used the total number of foreign cruise tourist arrivals as a measure of inbound cruise tourism demand and monthly cruise tourist arrivals to İzmir Cruise Port in the period of January 2005 ‐December 2013 were utilized to appropriate model. Experimental results showed that radial basis function (RBF neural network outperforms multi-layer perceptron (MLP and the generalised regression neural networks (GRNN in terms of forecasting accuracy. By the means of the obtained RBF neural network model, it has been forecasted the monthly inbound cruise tourism demand to İzmir for the year 2014.

Female Chess Players Outperform Expectations When Playing Men.

Science.gov (United States)

Stafford, Tom

2018-03-01

Stereotype threat has been offered as a potential explanation of differential performance between men and women in some cognitive domains. Questions remain about the reliability and generality of the phenomenon. Previous studies have found that stereotype threat is activated in female chess players when they are matched against male players. I used data from over 5.5 million games of international tournament chess and found no evidence of a stereotype-threat effect. In fact, female players outperform expectations when playing men. Further analysis showed no influence of degree of challenge, player age, nor prevalence of female role models in national chess leagues on differences in performance when women play men versus when they play women. Though this analysis contradicts one specific mechanism of influence of gender stereotypes, the persistent differences between male and female players suggest that systematic factors do exist and remain to be uncovered.

Figure-Ground Organization Emerges in a Deep Net with a Feedback Loop

OpenAIRE

Zipser, Karl

2015-01-01

We used a deep net to model how object-specific activation at the high levels of a hierarchical neural network could be fed back to modify representations at lower levels. We first identified a subset of nodes in the uppermost hidden layer that were preferentially activated by images of people. We then ran a procedure to recursively modify an image so as to increase activation of the 'person-selective' nodes. The image was modified by choosing a rectangular region (of random size and position...

NN-align. An artificial neural network-based alignment algorithm for MHC class II peptide binding prediction

Directory of Open Access Journals (Sweden)

Lund Ole

2009-09-01

Full Text Available Abstract Background The major histocompatibility complex (MHC molecule plays a central role in controlling the adaptive immune response to infections. MHC class I molecules present peptides derived from intracellular proteins to cytotoxic T cells, whereas MHC class II molecules stimulate cellular and humoral immunity through presentation of extracellularly derived peptides to helper T cells. Identification of which peptides will bind a given MHC molecule is thus of great importance for the understanding of host-pathogen interactions, and large efforts have been placed in developing algorithms capable of predicting this binding event. Results Here, we present a novel artificial neural network-based method, NN-align that allows for simultaneous identification of the MHC class II binding core and binding affinity. NN-align is trained using a novel training algorithm that allows for correction of bias in the training data due to redundant binding core representation. Incorporation of information about the residues flanking the peptide-binding core is shown to significantly improve the prediction accuracy. The method is evaluated on a large-scale benchmark consisting of six independent data sets covering 14 human MHC class II alleles, and is demonstrated to outperform other state-of-the-art MHC class II prediction methods. Conclusion The NN-align method is competitive with the state-of-the-art MHC class II peptide binding prediction algorithms. The method is publicly available at http://www.cbs.dtu.dk/services/NetMHCII-2.0.

Human Splice-Site Prediction with Deep Neural Networks.

Science.gov (United States)

Naito, Tatsuhiko

2018-04-18

Accurate splice-site prediction is essential to delineate gene structures from sequence data. Several computational techniques have been applied to create a system to predict canonical splice sites. For classification tasks, deep neural networks (DNNs) have achieved record-breaking results and often outperformed other supervised learning techniques. In this study, a new method of splice-site prediction using DNNs was proposed. The proposed system receives an input sequence data and returns an answer as to whether it is splice site. The length of input is 140 nucleotides, with the consensus sequence (i.e., "GT" and "AG" for the donor and acceptor sites, respectively) in the middle. Each input sequence model is applied to the pretrained DNN model that determines the probability that an input is a splice site. The model consists of convolutional layers and bidirectional long short-term memory network layers. The pretraining and validation were conducted using the data set tested in previously reported methods. The performance evaluation results showed that the proposed method can outperform the previous methods. In addition, the pattern learned by the DNNs was visualized as position frequency matrices (PFMs). Some of PFMs were very similar to the consensus sequence. The trained DNN model and the brief source code for the prediction system are uploaded. Further improvement will be achieved following the further development of DNNs.

Implementation of a pulse coupled neural network in FPGA.

Science.gov (United States)

Waldemark, J; Millberg, M; Lindblad, T; Waldemark, K; Becanovic, V

2000-06-01

The Pulse Coupled neural network, PCNN, is a biologically inspired neural net and it can be used in various image analysis applications, e.g. time-critical applications in the field of image pre-processing like segmentation, filtering, etc. a VHDL implementation of the PCNN targeting FPGA was undertaken and the results presented here. The implementation contains many interesting features. By pipelining the PCNN structure a very high throughput of 55 million neuron iterations per second could be achieved. By making the coefficients re-configurable during operation, a complete recognition system could be implemented on one, or maybe two, chip(s). Reconsidering the ranges and resolutions of the constants may save a lot of hardware, since the higher resolution requires larger multipliers, adders, memories etc.

Coloured Petri Nets

DEFF Research Database (Denmark)

Jensen, Kurt

1987-01-01

The author describes a Petri net model, called coloured Petri nets (CP-nets), by means of which it is possible to describe large systems without having to cope with unnecessary details. The author introduces CP-nets and provide a first impression of their modeling power and the suitability...

Adaptive control using a hybrid-neural model: application to a polymerisation reactor

Directory of Open Access Journals (Sweden)

Cubillos F.

2001-01-01

Full Text Available This work presents the use of a hybrid-neural model for predictive control of a plug flow polymerisation reactor. The hybrid-neural model (HNM is based on fundamental conservation laws associated with a neural network (NN used to model the uncertain parameters. By simulations, the performance of this approach was studied for a peroxide-initiated styrene tubular reactor. The HNM was synthesised for a CSTR reactor with a radial basis function neural net (RBFN used to estimate the reaction rates recursively. The adaptive HNM was incorporated in two model predictive control strategies, a direct synthesis scheme and an optimum steady state scheme. Tests for servo and regulator control showed excellent behaviour following different setpoint variations, and rejecting perturbations. The good generalisation and training capacities of hybrid models, associated with the simplicity and robustness characteristics of the MPC formulations, make an attractive combination for the control of a polymerisation reactor.

Net one, net two: the primary care network income statement.

Science.gov (United States)

Halley, M D; Little, A W

1999-10-01

Although hospital-owned primary care practices have been unprofitable for most hospitals, some hospitals are achieving competitive advantage and sustainable practice operations. A key to the success of some has been a net income reporting tool that separates practice operating expenses from the costs of creating and operating a network of practices to help healthcare organization managers, physicians, and staff to identify opportunities to improve the network's financial performance. This "Net One, Net Two" reporting allows operations leadership to be held accountable for Net One expenses and strategic leadership to be held accountable for Net Two expenses.

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method.

Science.gov (United States)

Guo, Xinyu; Dominick, Kelli C; Minai, Ali A; Li, Hailong; Erickson, Craig A; Lu, Long J

2017-01-01

The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t -test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method

Directory of Open Access Journals (Sweden)

Xinyu Guo

2017-08-01

Full Text Available The whole-brain functional connectivity (FC pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes. Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150. Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t-test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross

Application of neural networks to seismic active control

International Nuclear Information System (INIS)

Tang, Yu.

1995-01-01

An exploratory study on seismic active control using an artificial neural network (ANN) is presented in which a singledegree-of-freedom (SDF) structural system is controlled by a trained neural network. A feed-forward neural network and the backpropagation training method are used in the study. In backpropagation training, the learning rate is determined by ensuring the decrease of the error function at each training cycle. The training patterns for the neural net are generated randomly. Then, the trained ANN is used to compute the control force according to the control algorithm. The control strategy proposed herein is to apply the control force at every time step to destroy the build-up of the system response. The ground motions considered in the simulations are the N21E and N69W components of the Lake Hughes No. 12 record that occurred in the San Fernando Valley in California on February 9, 1971. Significant reduction of the structural response by one order of magnitude is observed. Also, it is shown that the proposed control strategy has the ability to reduce the peak that occurs during the first few cycles of the time history. These promising results assert the potential of applying ANNs to active structural control under seismic loads

Evaluation of the maximum-likelihood adaptive neural system (MLANS) applications to noncooperative IFF

Science.gov (United States)

Chernick, Julian A.; Perlovsky, Leonid I.; Tye, David M.

1994-06-01

This paper describes applications of maximum likelihood adaptive neural system (MLANS) to the characterization of clutter in IR images and to the identification of targets. The characterization of image clutter is needed to improve target detection and to enhance the ability to compare performance of different algorithms using diverse imagery data. Enhanced unambiguous IFF is important for fratricide reduction while automatic cueing and targeting is becoming an ever increasing part of operations. We utilized MLANS which is a parametric neural network that combines optimal statistical techniques with a model-based approach. This paper shows that MLANS outperforms classical classifiers, the quadratic classifier and the nearest neighbor classifier, because on the one hand it is not limited to the usual Gaussian distribution assumption and can adapt in real time to the image clutter distribution; on the other hand MLANS learns from fewer samples and is more robust than the nearest neighbor classifiers. Future research will address uncooperative IFF using fused IR and MMW data.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

Science.gov (United States)

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

Science.gov (United States)

McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

2018-04-01

Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Automatic Seismic-Event Classification with Convolutional Neural Networks.

Science.gov (United States)

Bueno Rodriguez, A.; Titos Luzón, M.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

2017-12-01

Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and

On the Reduction of Computational Complexity of Deep Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Partha Maji

2018-04-01

Full Text Available Deep convolutional neural networks (ConvNets, which are at the heart of many new emerging applications, achieve remarkable performance in audio and visual recognition tasks. Unfortunately, achieving accuracy often implies significant computational costs, limiting deployability. In modern ConvNets it is typical for the convolution layers to consume the vast majority of computational resources during inference. This has made the acceleration of these layers an important research area in academia and industry. In this paper, we examine the effects of co-optimizing the internal structures of the convolutional layers and underlying implementation of fundamental convolution operation. We demonstrate that a combination of these methods can have a big impact on the overall speedup of a ConvNet, achieving a ten-fold increase over baseline. We also introduce a new class of fast one-dimensional (1D convolutions for ConvNets using the Toom–Cook algorithm. We show that our proposed scheme is mathematically well-grounded, robust, and does not require any time-consuming retraining, while still achieving speedups solely from convolutional layers with no loss in baseline accuracy.

Development of a neural net paradigm that predicts simulator sickness

Energy Technology Data Exchange (ETDEWEB)

Allgood, G.O.

1993-03-01

A disease exists that affects pilots and aircrew members who use Navy Operational Flight Training Systems. This malady, commonly referred to as simulator sickness and whose symptomatology closely aligns with that of motion sickness, can compromise the use of these systems because of a reduced utilization factor, negative transfer of training, and reduction in combat readiness. A report is submitted that develops an artificial neural network (ANN) and behavioral model that predicts the onset and level of simulator sickness in the pilots and aircrews who sue these systems. It is proposed that the paradigm could be implemented in real time as a biofeedback monitor to reduce the risk to users of these systems. The model captures the neurophysiological impact of use (human-machine interaction) by developing a structure that maps the associative and nonassociative behavioral patterns (learned expectations) and vestibular (otolith and semicircular canals of the inner ear) and tactile interaction, derived from system acceleration profiles, onto an abstract space that predicts simulator sickness for a given training flight.

View-invariant gait recognition method by three-dimensional convolutional neural network

Science.gov (United States)

Xing, Weiwei; Li, Ying; Zhang, Shunli

2018-01-01

Gait as an important biometric feature can identify a human at a long distance. View change is one of the most challenging factors for gait recognition. To address the cross view issues in gait recognition, we propose a view-invariant gait recognition method by three-dimensional (3-D) convolutional neural network. First, 3-D convolutional neural network (3DCNN) is introduced to learn view-invariant feature, which can capture the spatial information and temporal information simultaneously on normalized silhouette sequences. Second, a network training method based on cross-domain transfer learning is proposed to solve the problem of the limited gait training samples. We choose the C3D as the basic model, which is pretrained on the Sports-1M and then fine-tune C3D model to adapt gait recognition. In the recognition stage, we use the fine-tuned model to extract gait features and use Euclidean distance to measure the similarity of gait sequences. Sufficient experiments are carried out on the CASIA-B dataset and the experimental results demonstrate that our method outperforms many other methods.

Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction.

Science.gov (United States)

Watanabe, Eiji; Kitaoka, Akiyoshi; Sakamoto, Kiwako; Yasugi, Masaki; Tanaka, Kenta

2018-01-01

The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning) predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research.

Development of Novel Gas Brand Anti-Piracy System based on BP Neural Networks

Energy Technology Data Exchange (ETDEWEB)

Wang, L [School of Aeronautics and Astronautics, Tongji University, Shanghai (China); Zhang, Y Y [Chinese-German School of Postgraduate Studies, Tongji University (China); Ding, L [Chinese-German School of Postgraduate Studies, Tongji University (China)

2006-10-15

The Wireless-net Close-loop gas brand anti-piracy system introduced in this paper is a new type of brand piracy technical product based on BP neural network. It is composed by gas brand piracy label possessing gas exhalation resource, ARM embedded gas-detector, GPRS wireless module and data base of merchandise information. First, the system obtains the information on the special label through gas sensor array ,then the attained signals are transferred into ARM Embedded board and identified by artificial neural network, and finally turns back the outcome of data collection and identification to the manufactures with the help of GPRS module.

Development of Novel Gas Brand Anti-Piracy System based on BP Neural Networks

Science.gov (United States)

Wang, L.; Zhang, Y. Y.; Ding, L.

2006-10-01

The Wireless-net Close-loop gas brand anti-piracy system introduced in this paper is a new type of brand piracy technical product based on BP neural network. It is composed by gas brand piracy label possessing gas exhalation resource, ARM embedded gas-detector, GPRS wireless module and data base of merchandise information. First, the system obtains the information on the special label through gas sensor array ,then the attained signals are transferred into ARM Embedded board and identified by artificial neural network, and finally turns back the outcome of data collection and identification to the manufactures with the help of GPRS module.

Development of Novel Gas Brand Anti-Piracy System based on BP Neural Networks

International Nuclear Information System (INIS)

Wang, L; Zhang, Y Y; Ding, L

2006-01-01

The Wireless-net Close-loop gas brand anti-piracy system introduced in this paper is a new type of brand piracy technical product based on BP neural network. It is composed by gas brand piracy label possessing gas exhalation resource, ARM embedded gas-detector, GPRS wireless module and data base of merchandise information. First, the system obtains the information on the special label through gas sensor array ,then the attained signals are transferred into ARM Embedded board and identified by artificial neural network, and finally turns back the outcome of data collection and identification to the manufactures with the help of GPRS module

Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network

Science.gov (United States)

Liu, Tao; Li, Ying; Cao, Ying; Shen, Qiang

2017-10-01

This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.

Wavelet-based higher-order neural networks for mine detection in thermal IR imagery

Science.gov (United States)

Baertlein, Brian A.; Liao, Wen-Jiao

2000-08-01

An image processing technique is described for the detection of miens in RI imagery. The proposed technique is based on a third-order neural network, which processes the output of a wavelet packet transform. The technique is inherently invariant to changes in signature position, rotation and scaling. The well-known memory limitations that arise with higher-order neural networks are addressed by (1) the data compression capabilities of wavelet packets, (2) protections of the image data into a space of similar triangles, and (3) quantization of that 'triangle space'. Using these techniques, image chips of size 28 by 28, which would require 0(109) neural net weights, are processed by a network having 0(102) weights. ROC curves are presented for mine detection in real and simulated imagery.

Deep learning with convolutional neural networks for EEG decoding and visualization.

Science.gov (United States)

Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-11-01

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

Deep learning with convolutional neural networks for EEG decoding and visualization

Science.gov (United States)

Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-01-01

Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

A modified backpropagation algorithm for training neural networks on data with error bars

International Nuclear Information System (INIS)

Gernoth, K.A.; Clark, J.W.

1994-08-01

A method is proposed for training multilayer feedforward neural networks on data contaminated with noise. Specifically, we consider the case that the artificial neural system is required to learn a physical mapping when the available values of the target variable are subject to experimental uncertainties, but are characterized by error bars. The proposed method, based on maximum likelihood criterion for parameter estimation, involves simple modifications of the on-line backpropagation learning algorithm. These include incorporation of the error-bar assignments in a pattern-specific learning rate, together with epochal updating of a new measure of model accuracy that replaces the usual mean-square error. The extended backpropagation algorithm is successfully tested on two problems relevant to the modelling of atomic-mass systematics by neural networks. Provided the underlying mapping is reasonably smooth, neural nets trained with the new procedure are able to learn the true function to a good approximation even in the presence of high levels of Gaussian noise. (author). 26 refs, 2 figs, 5 tabs

Deep Recurrent Neural Networks for Human Activity Recognition

Directory of Open Access Journals (Sweden)

Abdulmajid Murad

2017-11-01

Full Text Available Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM and k-nearest neighbors (KNN. Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs and CNNs.

Deep Recurrent Neural Networks for Human Activity Recognition.

Science.gov (United States)

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

Science.gov (United States)

Hsu, Ken-Yuh (Editor); Liu, Hua-Kuang (Editor)

1992-01-01

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

Science.gov (United States)

Hsu, Ken-Yuh; Liu, Hua-Kuang

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Targets Mask U-Net for Wind Turbines Detection in Remote Sensing Images

Science.gov (United States)

Han, M.; Wang, H.; Wang, G.; Liu, Y.

2018-04-01

To detect wind turbines precisely and quickly in very high resolution remote sensing images (VHRRSI) we propose target mask U-Net. This convolution neural network (CNN), which is carefully designed to be a wide-field detector, models the pixel class assignment to wind turbines and their context information. The shadow, which is the context information of the target in this study, has been regarded as part of a wind turbine instance. We have trained the target mask U-Net on training dataset, which is composed of down sampled image blocks and instance mask blocks. Some post-processes have been integrated to eliminate wrong spots and produce bounding boxes of wind turbine instances. The evaluation metrics prove the reliability and effectiveness of our method for the average F1-score of our detection method is up to 0.97. The comparison of detection accuracy and time consuming with the weakly supervised targets detection method based on CNN illustrates the superiority of our method.

Learning and Generalisation in Neural Networks with Local Preprocessing

OpenAIRE

Kutsia, Merab

2007-01-01

We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the net...

Auto-control of pumping operations in sewerage systems by rule-based fuzzy neural networks

Directory of Open Access Journals (Sweden)

Y.-M. Chiang

2011-01-01

Full Text Available Pumping stations play an important role in flood mitigation in metropolitan areas. The existing sewerage systems, however, are facing a great challenge of fast rising peak flow resulting from urbanization and climate change. It is imperative to construct an efficient and accurate operating prediction model for pumping stations to simulate the drainage mechanism for discharging the rainwater in advance. In this study, we propose two rule-based fuzzy neural networks, adaptive neuro-fuzzy inference system (ANFIS and counterpropagation fuzzy neural network for on-line predicting of the number of open and closed pumps of a pivotal pumping station in Taipei city up to a lead time of 20 min. The performance of ANFIS outperforms that of CFNN in terms of model efficiency, accuracy, and correctness. Furthermore, the results not only show the predictive water levels do contribute to the successfully operating pumping stations but also demonstrate the applicability and reliability of ANFIS in automatically controlling the urban sewerage systems.

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

Science.gov (United States)

Meszlényi, Regina J; Buza, Krisztian; Vidnyánszky, Zoltán

2017-01-01

Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

Optimization of artificial neural networks for the reconstruction of the neutrons spectrum and their equivalent doses; Optimizacion de redes neuronales artificiales para la reconstruccion del espectro de neutrones y sus dosis equivalentes

Energy Technology Data Exchange (ETDEWEB)

Reyes A, A.; Ortiz R, J. M.; Reyes H, A.; Castaneda M, R.; Solis S, L. O.; Vega C, H. R., E-mail: art8291@hotmail.com [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica, Av. Lopez Velarde No. 801, Col. Centro, 98000 Zacatecas (Mexico)

2014-08-15

In this work was used the robust design methodology of artificial neural networks to determine a good topology of net able to solve with efficiency the problems of neutrons spectrometry and dosimetry. For the design of the topology of optimized net 36 different net architectures based on an orthogonal arrangement with a configuration L{sub 9}(3{sup 4}), L{sub 4}(3{sup 2}) were trained. For the training of the neural networks, was used a computer code developed in the ambient of Mat lab programming, which automates the process and analysis of the information, reducing the time used in this activity considerably for the investigator. For the training of the propagation nets forward was utilized a neutrons spectrum compendium published by the International Atomic Energy Agency, where of the total 80% was used for the training and 20% for the test, it trained with an inverse propagation algorithm being the entrance data the count rates corresponding to the 7 spheres of the spectrometric system of Bonner spheres, as exit data, the neural network obtains the neutrons spectrum expressed in 60 energy groups and are calculated of simultaneous way 15 dosimetric quantities. (Author)

Adaptive Near-Optimal Multiuser Detection Using a Stochastic and Hysteretic Hopfield Net Receiver

Directory of Open Access Journals (Sweden)

Gábor Jeney

2003-01-01

Full Text Available This paper proposes a novel adaptive MUD algorithm for a wide variety (practically any kind of interference limited systems, for example, code division multiple access (CDMA. The algorithm is based on recently developed neural network techniques and can perform near optimal detection in the case of unknown channel characteristics. The proposed algorithm consists of two main blocks; one estimates the symbols sent by the transmitters, the other identifies each channel of the corresponding communication links. The estimation of symbols is carried out either by a stochastic Hopfield net (SHN or by a hysteretic neural network (HyNN or both. The channel identification is based on either the self-organizing feature map (SOM or the learning vector quantization (LVQ. The combination of these two blocks yields a powerful real-time detector with near optimal performance. The performance is analyzed by extensive simulations.

Application of deconvolution interferometry with both Hi-net and KiK-net data

Science.gov (United States)

Nakata, N.

2013-12-01

Application of deconvolution interferometry to wavefields observed by KiK-net, a strong-motion recording network in Japan, is useful for estimating wave velocities and S-wave splitting in the near surface. Using this technique, for example, Nakata and Snieder (2011, 2012) found changed in velocities caused by Tohoku-Oki earthquake in Japan. At the location of the borehole accelerometer of each KiK-net station, a velocity sensor is also installed as a part of a high-sensitivity seismograph network (Hi-net). I present a technique that uses both Hi-net and KiK-net records for computing deconvolution interferometry. The deconvolved waveform obtained from the combination of Hi-net and KiK-net data is similar to the waveform computed from KiK-net data only, which indicates that one can use Hi-net wavefields for deconvolution interferometry. Because Hi-net records have a high signal-to-noise ratio (S/N) and high dynamic resolution, the S/N and the quality of amplitude and phase of deconvolved waveforms can be improved with Hi-net data. These advantages are especially important for short-time moving-window seismic interferometry and deconvolution interferometry using later coda waves.

Drug-Drug Interaction Extraction via Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Shengyu Liu

2016-01-01

Full Text Available Drug-drug interaction (DDI extraction as a typical relation extraction task in natural language processing (NLP has always attracted great attention. Most state-of-the-art DDI extraction systems are based on support vector machines (SVM with a large number of manually defined features. Recently, convolutional neural networks (CNN, a robust machine learning method which almost does not need manually defined features, has exhibited great potential for many NLP tasks. It is worth employing CNN for DDI extraction, which has never been investigated. We proposed a CNN-based method for DDI extraction. Experiments conducted on the 2013 DDIExtraction challenge corpus demonstrate that CNN is a good choice for DDI extraction. The CNN-based DDI extraction method achieves an F-score of 69.75%, which outperforms the existing best performing method by 2.75%.

Lifelong bilingualism maintains neural efficiency for cognitive control in aging.

Science.gov (United States)

Gold, Brian T; Kim, Chobok; Johnson, Nathan F; Kryscio, Richard J; Smith, Charles D

2013-01-09

Recent behavioral data have shown that lifelong bilingualism can maintain youthful cognitive control abilities in aging. Here, we provide the first direct evidence of a neural basis for the bilingual cognitive control boost in aging. Two experiments were conducted, using a perceptual task-switching paradigm, including a total of 110 participants. In Experiment 1, older adult bilinguals showed better perceptual switching performance than their monolingual peers. In Experiment 2, younger and older adult monolinguals and bilinguals completed the same perceptual task-switching experiment while functional magnetic resonance imaging (fMRI) was performed. Typical age-related performance reductions and fMRI activation increases were observed. However, like younger adults, bilingual older adults outperformed their monolingual peers while displaying decreased activation in left lateral frontal cortex and cingulate cortex. Critically, this attenuation of age-related over-recruitment associated with bilingualism was directly correlated with better task-switching performance. In addition, the lower blood oxygenation level-dependent response in frontal regions accounted for 82% of the variance in the bilingual task-switching reaction time advantage. These results suggest that lifelong bilingualism offsets age-related declines in the neural efficiency for cognitive control processes.

Deep Convolutional Neural Networks for Endotracheal Tube Position and X-ray Image Classification: Challenges and Opportunities.

Science.gov (United States)

Lakhani, Paras

2017-08-01

The goal of this study is to evaluate the efficacy of deep convolutional neural networks (DCNNs) in differentiating subtle, intermediate, and more obvious image differences in radiography. Three different datasets were created, which included presence/absence of the endotracheal (ET) tube (n = 300), low/normal position of the ET tube (n = 300), and chest/abdominal radiographs (n = 120). The datasets were split into training, validation, and test. Both untrained and pre-trained deep neural networks were employed, including AlexNet and GoogLeNet classifiers, using the Caffe framework. Data augmentation was performed for the presence/absence and low/normal ET tube datasets. Receiver operating characteristic (ROC), area under the curves (AUC), and 95% confidence intervals were calculated. Statistical differences of the AUCs were determined using a non-parametric approach. The pre-trained AlexNet and GoogLeNet classifiers had perfect accuracy (AUC 1.00) in differentiating chest vs. abdominal radiographs, using only 45 training cases. For more difficult datasets, including the presence/absence and low/normal position endotracheal tubes, more training cases, pre-trained networks, and data-augmentation approaches were helpful to increase accuracy. The best-performing network for classifying presence vs. absence of an ET tube was still very accurate with an AUC of 0.99. However, for the most difficult dataset, such as low vs. normal position of the endotracheal tube, DCNNs did not perform as well, but achieved a reasonable AUC of 0.81.

StarNet: An application of deep learning in the analysis of stellar spectra

Science.gov (United States)

Kielty, Collin; Bialek, Spencer; Fabbro, Sebastien; Venn, Kim; O'Briain, Teaghan; Jahandar, Farbod; Monty, Stephanie

2018-06-01

In an era when spectroscopic surveys are capable of collecting spectra for hundreds of thousands of stars, fast and efficient analysis methods are required to maximize scientific impact. These surveys provide a homogeneous database of stellar spectra that are ideal for machine learning applications. In this poster, we present StarNet: a convolutional neural network model applied to the analysis of both SDSS-III APOGEE DR13 and synthetic stellar spectra. When trained on synthetic spectra alone, the calculated stellar parameters (temperature, surface gravity, and metallicity) are of excellent precision and accuracy for both APOGEE data and synthetic data, over a wide range of signal-to-noise ratios. While StarNet was developed using the APOGEE observed spectra and corresponding ASSeT synthetic grid, we suggest that this technique is applicable to other spectral resolutions, spectral surveys, and wavelength regimes. As a demonstration of this, we present a StarNet model trained on lower resolution, R=6000, IR synthetic spectra, describing the spectra delivered by Gemini/NIFS and the forthcoming Gemini/GIRMOS instrument (PI Sivanandam, UToronto). Preliminary results suggest that the stellar parameters determined from this low resolution StarNet model are comparable in precision to the high-resolution APOGEE results. The success of StarNet at lower resolution can be attributed to (1) a large training set of synthetic spectra (N ~200,000) with a priori stellar labels, and (2) the use of the entire spectrum in the solution rather than a few weighted windows, which are common methods in other spectral analysis tools (e.g. FERRE or The Cannon). Remaining challenges in our StarNet applications include rectification, continuum normalization, and wavelength coverage. Solutions to these problems could be used to guide decisions made in the development of future spectrographs, spectroscopic surveys, and data reduction pipelines, such as for the future MSE.

Progressively expanded neural network for automatic material identification in hyperspectral imagery

Science.gov (United States)

Paheding, Sidike

The science of hyperspectral remote sensing focuses on the exploitation of the spectral signatures of various materials to enhance capabilities including object detection, recognition, and material characterization. Hyperspectral imagery (HSI) has been extensively used for object detection and identification applications since it provides plenty of spectral information to uniquely identify materials by their reflectance spectra. HSI-based object detection algorithms can be generally classified into stochastic and deterministic approaches. Deterministic approaches are comparatively simple to apply since it is usually based on direct spectral similarity such as spectral angles or spectral correlation. In contrast, stochastic algorithms require statistical modeling and estimation for target class and non-target class. Over the decades, many single class object detection methods have been proposed in the literature, however, deterministic multiclass object detection in HSI has not been explored. In this work, we propose a deterministic multiclass object detection scheme, named class-associative spectral fringe-adjusted joint transform correlation. Human brain is capable of simultaneously processing high volumes of multi-modal data received every second of the day. In contrast, a machine sees input data simply as random binary numbers. Although machines are computationally efficient, they are inferior when comes to data abstraction and interpretation. Thus, mimicking the learning strength of human brain has been current trend in artificial intelligence. In this work, we present a biological inspired neural network, named progressively expanded neural network (PEN Net), based on nonlinear transformation of input neurons to a feature space for better pattern differentiation. In PEN Net, discrete fixed excitations are disassembled and scattered in the feature space as a nonlinear line. Each disassembled element on the line corresponds to a pattern with similar features

Forcast of TEXT plasma disruptions using soft X-rays as input signal in a neural network

International Nuclear Information System (INIS)

Vannucci, A.; Oliveira, K.A.; Tajima, T.

1998-02-01

A feed-forward neural network with two hidden layers is used in this work to forecast major and minor disruptive instabilities in TEXT discharges. Using soft X-ray signals as input data, the neural net is trained with one disruptive plasma pulse, and a different disruptive discharge is used for validation. After being properly trained the networks, with the same set of weights. is then used to forecast disruptions in two others different plasma pulses. It is observed that the neural net is able to predict the incoming of a disruption more than 3 ms in advance. This time interval is almost three times longer than the one already obtained previously when magnetic signal from a Mirnov coil was used to feed the neural networks with. To our own eye we fail to see any indication of an upcoming disruption from the experimental data this far back from the time of disruption. Finally, from what we observe in the predictive behavior of our network, speculations are made whether the disruption triggering mechanism would be associated to an increase of the m = 2 magnetic island, that disturbs the central part of the plasma column afterwards or, in face of the results from this work, the initial perturbation would have occurred first in the central part of the plasma column, within the q = 1 magnetic surface, and then the m = 2 MHD mode would be destabilized afterwards

Knowledge base and neural network approach for protein secondary structure prediction.

Science.gov (United States)

Patel, Maulika S; Mazumdar, Himanshu S

2014-11-21

Protein structure prediction is of great relevance given the abundant genomic and proteomic data generated by the genome sequencing projects. Protein secondary structure prediction is addressed as a sub task in determining the protein tertiary structure and function. In this paper, a novel algorithm, KB-PROSSP-NN, which is a combination of knowledge base and modeling of the exceptions in the knowledge base using neural networks for protein secondary structure prediction (PSSP), is proposed. The knowledge base is derived from a proteomic sequence-structure database and consists of the statistics of association between the 5-residue words and corresponding secondary structure. The predicted results obtained using knowledge base are refined with a Backpropogation neural network algorithm. Neural net models the exceptions of the knowledge base. The Q3 accuracy of 90% and 82% is achieved on the RS126 and CB396 test sets respectively which suggest improvement over existing state of art methods. Copyright © 2014 Elsevier Ltd. All rights reserved.

Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction

Directory of Open Access Journals (Sweden)

Eiji Watanabe

2018-03-01

Full Text Available The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research.

Adaptive Robot Control – An Experimental Comparison

Directory of Open Access Journals (Sweden)

Francesco Alonge

2012-11-01

Full Text Available This paper deals with experimental comparison between stable adaptive controllers of robotic manipulators based on Model Based Adaptive, Neural Network and Wavelet -Based control. The above control methods were compared with each other in terms of computational efficiency, need for accurate mathematical model of the manipulator and tracking performances. An original management algorithm of the Wavelet Network control scheme has been designed, with the aim of constructing the net automatically during the trajectory tracking, without the need to tune it to the trajectory itself. Experimental tests, carried out on a planar two link manipulator, show that the Wavelet-Based control scheme, with the new management algorithm, outperforms the conventional Model-Based schemes in the presence of structural uncertainties in the mathematical model of the robot, without pre-training and more efficiently than the Neural Network approach.

Net Neutrality

DEFF Research Database (Denmark)

Savin, Andrej

2017-01-01

Repealing “net neutrality” in the US will have no bearing on Internet freedom or security there or anywhere else.......Repealing “net neutrality” in the US will have no bearing on Internet freedom or security there or anywhere else....

Annotating Coloured Petri Nets

DEFF Research Database (Denmark)

Lindstrøm, Bo; Wells, Lisa Marie

2002-01-01

Coloured Petri nets (CP-nets) can be used for several fundamentally different purposes like functional analysis, performance analysis, and visualisation. To be able to use the corresponding tool extensions and libraries it is sometimes necessary to include extra auxiliary information in the CP......-net. An example of such auxiliary information is a counter which is associated with a token to be able to do performance analysis. Modifying colour sets and arc inscriptions in a CP-net to support a specific use may lead to creation of several slightly different CP-nets – only to support the different uses...... of the same basic CP-net. One solution to this problem is that the auxiliary information is not integrated into colour sets and arc inscriptions of a CP-net, but is kept separately. This makes it easy to disable this auxiliary information if a CP-net is to be used for another purpose. This paper proposes...

Efficient airport detection using region-based fully convolutional neural networks

Science.gov (United States)

Xin, Peng; Xu, Yuelei; Zhang, Xulei; Ma, Shiping; Li, Shuai; Lv, Chao

2018-04-01

This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

Tree-based indexing for real-time ConvNet landmark-based visual place recognition

Directory of Open Access Journals (Sweden)

Yi Hou

2017-01-01

Full Text Available Recent impressive studies on using ConvNet landmarks for visual place recognition take an approach that involves three steps: (a detection of landmarks, (b description of the landmarks by ConvNet features using a convolutional neural network, and (c matching of the landmarks in the current view with those in the database views. Such an approach has been shown to achieve the state-of-the-art accuracy even under significant viewpoint and environmental changes. However, the computational burden in step (c significantly prevents this approach from being applied in practice, due to the complexity of linear search in high-dimensional space of the ConvNet features. In this article, we propose two simple and efficient search methods to tackle this issue. Both methods are built upon tree-based indexing. Given a set of ConvNet features of a query image, the first method directly searches the features’ approximate nearest neighbors in a tree structure that is constructed from ConvNet features of database images. The database images are voted on by features in the query image, according to a lookup table which maps each ConvNet feature to its corresponding database image. The database image with the highest vote is considered the solution. Our second method uses a coarse-to-fine procedure: the coarse step uses the first method to coarsely find the top-N database images, and the fine step performs a linear search in Hamming space of the hash codes of the ConvNet features to determine the best match. Experimental results demonstrate that our methods achieve real-time search performance on five data sets with different sizes and various conditions. Most notably, by achieving an average search time of 0.035 seconds/query, our second method improves the matching efficiency by the three orders of magnitude over a linear search baseline on a database with 20,688 images, with negligible loss in place recognition accuracy.

Sentiment analysis: a comparison of deep learning neural network algorithm with SVM and naϊve Bayes for Indonesian text

Science.gov (United States)

Calvin Frans Mariel, Wahyu; Mariyah, Siti; Pramana, Setia

2018-03-01

Deep learning is a new era of machine learning techniques that essentially imitate the structure and function of the human brain. It is a development of deeper Artificial Neural Network (ANN) that uses more than one hidden layer. Deep Learning Neural Network has a great ability on recognizing patterns from various data types such as picture, audio, text, and many more. In this paper, the authors tries to measure that algorithm’s ability by applying it into the text classification. The classification task herein is done by considering the content of sentiment in a text which is also called as sentiment analysis. By using several combinations of text preprocessing and feature extraction techniques, we aim to compare the precise modelling results of Deep Learning Neural Network with the other two commonly used algorithms, the Naϊve Bayes and Support Vector Machine (SVM). This algorithm comparison uses Indonesian text data with balanced and unbalanced sentiment composition. Based on the experimental simulation, Deep Learning Neural Network clearly outperforms the Naϊve Bayes and SVM and offers a better F-1 Score while for the best feature extraction technique which improves that modelling result is Bigram.

Antenna analysis using neural networks

Science.gov (United States)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern

Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks

Directory of Open Access Journals (Sweden)

Salim Lahmiri

2014-07-01

Full Text Available This paper presents a forecasting model that integrates the discrete wavelet transform (DWT and backpropagation neural networks (BPNN for predicting financial time series. The presented model first uses the DWT to decompose the financial time series data. Then, the obtained approximation (low-frequency and detail (high-frequency components after decomposition of the original time series are used as input variables to forecast future stock prices. Indeed, while high-frequency components can capture discontinuities, ruptures and singularities in the original data, low-frequency components characterize the coarse structure of the data, to identify the long-term trends in the original data. As a result, high-frequency components act as a complementary part of low-frequency components. The model was applied to seven datasets. For all of the datasets, accuracy measures showed that the presented model outperforms a conventional model that uses only low-frequency components. In addition, the presented model outperforms both the well-known auto-regressive moving-average (ARMA model and the random walk (RW process.

NetSig

DEFF Research Database (Denmark)

Horn, Heiko; Lawrence, Michael S; Chouinard, Candace R

2018-01-01

Methods that integrate molecular network information and tumor genome data could complement gene-based statistical tests to identify likely new cancer genes; but such approaches are challenging to validate at scale, and their predictive value remains unclear. We developed a robust statistic (Net......Sig) that integrates protein interaction networks with data from 4,742 tumor exomes. NetSig can accurately classify known driver genes in 60% of tested tumor types and predicts 62 new driver candidates. Using a quantitative experimental framework to determine in vivo tumorigenic potential in mice, we found that Net......Sig candidates induce tumors at rates that are comparable to those of known oncogenes and are ten-fold higher than those of random genes. By reanalyzing nine tumor-inducing NetSig candidates in 242 patients with oncogene-negative lung adenocarcinomas, we find that two (AKT2 and TFDP2) are significantly amplified...

Improved Shape Parameter Estimation in Pareto Distributed Clutter with Neural Networks

Directory of Open Access Journals (Sweden)

José Raúl Machado-Fernández

2016-12-01

Full Text Available The main problem faced by naval radars is the elimination of the clutter input which is a distortion signal appearing mixed with target reflections. Recently, the Pareto distribution has been related to sea clutter measurements suggesting that it may provide a better fit than other traditional distributions. The authors propose a new method for estimating the Pareto shape parameter based on artificial neural networks. The solution achieves a precise estimation of the parameter, having a low computational cost, and outperforming the classic method which uses Maximum Likelihood Estimates (MLE. The presented scheme contributes to the development of the NATE detector for Pareto clutter, which uses the knowledge of clutter statistics for improving the stability of the detection, among other applications.

Learning Visual Basic NET

CERN Document Server

Liberty, Jesse

2009-01-01

Learning Visual Basic .NET is a complete introduction to VB.NET and object-oriented programming. By using hundreds of examples, this book demonstrates how to develop various kinds of applications--including those that work with databases--and web services. Learning Visual Basic .NET will help you build a solid foundation in .NET.

State-dependent, bidirectional modulation of neural network activity by endocannabinoids.

Science.gov (United States)

Piet, Richard; Garenne, André; Farrugia, Fanny; Le Masson, Gwendal; Marsicano, Giovanni; Chavis, Pascale; Manzoni, Olivier J

2011-11-16

The endocannabinoid (eCB) system and the cannabinoid CB1 receptor (CB1R) play key roles in the modulation of brain functions. Although actions of eCBs and CB1Rs are well described at the synaptic level, little is known of their modulation of neural activity at the network level. Using microelectrode arrays, we have examined the role of CB1R activation in the modulation of the electrical activity of rat and mice cortical neural networks in vitro. We find that exogenous activation of CB1Rs expressed on glutamatergic neurons decreases the spontaneous activity of cortical neural networks. Moreover, we observe that the net effect of the CB1R antagonist AM251 inversely correlates with the initial level of activity in the network: blocking CB1Rs increases network activity when basal network activity is low, whereas it depresses spontaneous activity when its initial level is high. Our results reveal a complex role of CB1Rs in shaping spontaneous network activity, and suggest that the outcome of endogenous neuromodulation on network function might be state dependent.

A modified dynamic evolving neural-fuzzy approach to modeling customer satisfaction for affective design.

Science.gov (United States)

Kwong, C K; Fung, K Y; Jiang, Huimin; Chan, K Y; Siu, Kin Wai Michael

2013-01-01

Affective design is an important aspect of product development to achieve a competitive edge in the marketplace. A neural-fuzzy network approach has been attempted recently to model customer satisfaction for affective design and it has been proved to be an effective one to deal with the fuzziness and non-linearity of the modeling as well as generate explicit customer satisfaction models. However, such an approach to modeling customer satisfaction has two limitations. First, it is not suitable for the modeling problems which involve a large number of inputs. Second, it cannot adapt to new data sets, given that its structure is fixed once it has been developed. In this paper, a modified dynamic evolving neural-fuzzy approach is proposed to address the above mentioned limitations. A case study on the affective design of mobile phones was conducted to illustrate the effectiveness of the proposed methodology. Validation tests were conducted and the test results indicated that: (1) the conventional Adaptive Neuro-Fuzzy Inference System (ANFIS) failed to run due to a large number of inputs; (2) the proposed dynamic neural-fuzzy model outperforms the subtractive clustering-based ANFIS model and fuzzy c-means clustering-based ANFIS model in terms of their modeling accuracy and computational effort.

A Modified Dynamic Evolving Neural-Fuzzy Approach to Modeling Customer Satisfaction for Affective Design

Directory of Open Access Journals (Sweden)

C. K. Kwong

2013-01-01

Full Text Available Affective design is an important aspect of product development to achieve a competitive edge in the marketplace. A neural-fuzzy network approach has been attempted recently to model customer satisfaction for affective design and it has been proved to be an effective one to deal with the fuzziness and non-linearity of the modeling as well as generate explicit customer satisfaction models. However, such an approach to modeling customer satisfaction has two limitations. First, it is not suitable for the modeling problems which involve a large number of inputs. Second, it cannot adapt to new data sets, given that its structure is fixed once it has been developed. In this paper, a modified dynamic evolving neural-fuzzy approach is proposed to address the above mentioned limitations. A case study on the affective design of mobile phones was conducted to illustrate the effectiveness of the proposed methodology. Validation tests were conducted and the test results indicated that: (1 the conventional Adaptive Neuro-Fuzzy Inference System (ANFIS failed to run due to a large number of inputs; (2 the proposed dynamic neural-fuzzy model outperforms the subtractive clustering-based ANFIS model and fuzzy c-means clustering-based ANFIS model in terms of their modeling accuracy and computational effort.

Bayesian neural adjustment of inhibitory control predicts emergence of problem stimulant use.

Science.gov (United States)

Harlé, Katia M; Stewart, Jennifer L; Zhang, Shunan; Tapert, Susan F; Yu, Angela J; Paulus, Martin P

2015-11-01

Bayesian ideal observer models quantify individuals' context- and experience-dependent beliefs and expectations about their environment, which provides a powerful approach (i) to link basic behavioural mechanisms to neural processing; and (ii) to generate clinical predictors for patient populations. Here, we focus on (ii) and determine whether individual differences in the neural representation of the need to stop in an inhibitory task can predict the development of problem use (i.e. abuse or dependence) in individuals experimenting with stimulants. One hundred and fifty-seven non-dependent occasional stimulant users, aged 18-24, completed a stop-signal task while undergoing functional magnetic resonance imaging. These individuals were prospectively followed for 3 years and evaluated for stimulant use and abuse/dependence symptoms. At follow-up, 38 occasional stimulant users met criteria for a stimulant use disorder (problem stimulant users), while 50 had discontinued use (desisted stimulant users). We found that those individuals who showed greater neural responses associated with Bayesian prediction errors, i.e. the difference between actual and expected need to stop on a given trial, in right medial prefrontal cortex/anterior cingulate cortex, caudate, anterior insula, and thalamus were more likely to exhibit problem use 3 years later. Importantly, these computationally based neural predictors outperformed clinical measures and non-model based neural variables in predicting clinical status. In conclusion, young adults who show exaggerated brain processing underlying whether to 'stop' or to 'go' are more likely to develop stimulant abuse. Thus, Bayesian cognitive models provide both a computational explanation and potential predictive biomarkers of belief processing deficits in individuals at risk for stimulant addiction. © The Author (2015). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please

Neural basis of stereotype-induced shifts in women's mental rotation performance.

Science.gov (United States)

Wraga, Maryjane; Helt, Molly; Jacobs, Emily; Sullivan, Kerry

2007-03-01

Recent negative focus on women's academic abilities has fueled disputes over gender disparities in the sciences. The controversy derives, in part, from women's relatively poorer performance in aptitude tests, many of which require skills of spatial reasoning. We used functional magnetic imaging to examine the neural structure underlying shifts in women's performance of a spatial reasoning task induced by positive and negative stereotypes. Three groups of participants performed a task involving imagined rotations of the self. Prior to scanning, the positive stereotype group was exposed to a false but plausible stereotype of women's superior perspective-taking abilities; the negative stereotype group was exposed to the pervasive stereotype that men outperform women on spatial tasks; and the control group received neutral information. The significantly poorer performance we found in the negative stereotype group corresponded to increased activation in brain regions associated with increased emotional load. In contrast, the significantly improved performance we found in the positive stereotype group was associated with increased activation in visual processing areas and, to a lesser degree, complex working memory processes. These findings suggest that stereotype messages affect the brain selectively, with positive messages producing relatively more efficient neural strategies than negative messages.

Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data.

Science.gov (United States)

Aliper, Alexander; Plis, Sergey; Artemov, Artem; Ulloa, Alvaro; Mamoshina, Polina; Zhavoronkov, Alex

2016-07-05

Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics, and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF-7, and PC-3 cell lines from the LINCS Project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled data set of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both pathway and gene level classification, DNN achieved high classification accuracy and convincingly outperformed the support vector machine (SVM) model on every multiclass classification problem, however, models based on pathway level data performed significantly better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development.

Feature Extraction and Fusion Using Deep Convolutional Neural Networks for Face Detection

Directory of Open Access Journals (Sweden)

Xiaojun Lu

2017-01-01

Full Text Available This paper proposes a method that uses feature fusion to represent images better for face detection after feature extraction by deep convolutional neural network (DCNN. First, with Clarifai net and VGG Net-D (16 layers, we learn features from data, respectively; then we fuse features extracted from the two nets. To obtain more compact feature representation and mitigate computation complexity, we reduce the dimension of the fused features by PCA. Finally, we conduct face classification by SVM classifier for binary classification. In particular, we exploit offset max-pooling to extract features with sliding window densely, which leads to better matches of faces and detection windows; thus the detection result is more accurate. Experimental results show that our method can detect faces with severe occlusion and large variations in pose and scale. In particular, our method achieves 89.24% recall rate on FDDB and 97.19% average precision on AFW.

Real-time classification of signals from three-component seismic sensors using neural nets

Science.gov (United States)

Bowman, B. C.; Dowla, F.

1992-05-01

Adaptive seismic data acquisition systems with capabilities of signal discrimination and event classification are important in treaty monitoring, proliferation, and earthquake early detection systems. Potential applications include monitoring underground chemical explosions, as well as other military, cultural, and natural activities where characteristics of signals change rapidly and without warning. In these applications, the ability to detect and interpret events rapidly without falling behind the influx of the data is critical. We developed a system for real-time data acquisition, analysis, learning, and classification of recorded events employing some of the latest technology in computer hardware, software, and artificial neural networks methods. The system is able to train dynamically, and updates its knowledge based on new data. The software is modular and hardware-independent; i.e., the front-end instrumentation is transparent to the analysis system. The software is designed to take advantage of the multiprocessing environment of the Unix operating system. The Unix System V shared memory and static RAM protocols for data access and the semaphore mechanism for interprocess communications were used. As the three-component sensor detects a seismic signal, it is displayed graphically on a color monitor using X11/Xlib graphics with interactive screening capabilities. For interesting events, the triaxial signal polarization is computed, a fast Fourier Transform (FFT) algorithm is applied, and the normalized power spectrum is transmitted to a backpropagation neural network for event classification. The system is currently capable of handling three data channels with a sampling rate of 500 Hz, which covers the bandwidth of most seismic events. The system has been tested in laboratory setting with artificial events generated in the vicinity of a three-component sensor.

Pro-Nets versus No-Nets: Differences in Urban Older Adults' Predilections for Internet Use

Science.gov (United States)

Cresci, M. Kay; Yarandi, Hossein N.; Morrell, Roger W.

2010-01-01

Enthusiasm for information technology (IT) is growing among older adults. Many older adults enjoy IT and the Internet (Pro-Nets), but others have no desire to use it (No-Nets). This study found that Pro-Nets and No-Nets were different on a number of variables that might predict IT use. No-Nets were older, had less education and income, were…

Automatic physical inference with information maximizing neural networks

Science.gov (United States)

Charnock, Tom; Lavaux, Guilhem; Wandelt, Benjamin D.

2018-04-01

Compressing large data sets to a manageable number of summaries that are informative about the underlying parameters vastly simplifies both frequentist and Bayesian inference. When only simulations are available, these summaries are typically chosen heuristically, so they may inadvertently miss important information. We introduce a simulation-based machine learning technique that trains artificial neural networks to find nonlinear functionals of data that maximize Fisher information: information maximizing neural networks (IMNNs). In test cases where the posterior can be derived exactly, likelihood-free inference based on automatically derived IMNN summaries produces nearly exact posteriors, showing that these summaries are good approximations to sufficient statistics. In a series of numerical examples of increasing complexity and astrophysical relevance we show that IMNNs are robustly capable of automatically finding optimal, nonlinear summaries of the data even in cases where linear compression fails: inferring the variance of Gaussian signal in the presence of noise, inferring cosmological parameters from mock simulations of the Lyman-α forest in quasar spectra, and inferring frequency-domain parameters from LISA-like detections of gravitational waveforms. In this final case, the IMNN summary outperforms linear data compression by avoiding the introduction of spurious likelihood maxima. We anticipate that the automatic physical inference method described in this paper will be essential to obtain both accurate and precise cosmological parameter estimates from complex and large astronomical data sets, including those from LSST and Euclid.

Experiments and simulation of a net closing mechanism for tether-net capture of space debris

Science.gov (United States)

Sharf, Inna; Thomsen, Benjamin; Botta, Eleonora M.; Misra, Arun K.

2017-10-01

This research addresses the design and testing of a debris containment system for use in a tether-net approach to space debris removal. The tether-net active debris removal involves the ejection of a net from a spacecraft by applying impulses to masses on the net, subsequent expansion of the net, the envelopment and capture of the debris target, and the de-orbiting of the debris via a tether to the chaser spacecraft. To ensure a debris removal mission's success, it is important that the debris be successfully captured and then, secured within the net. To this end, we present a concept for a net closing mechanism, which we believe will permit consistently successful debris capture via a simple and unobtrusive design. This net closing system functions by extending the main tether connecting the chaser spacecraft and the net vertex to the perimeter and around the perimeter of the net, allowing the tether to actuate closure of the net in a manner similar to a cinch cord. A particular embodiment of the design in a laboratory test-bed is described: the test-bed itself is comprised of a scaled-down tether-net, a supporting frame and a mock-up debris. Experiments conducted with the facility demonstrate the practicality of the net closing system. A model of the net closure concept has been integrated into the previously developed dynamics simulator of the chaser/tether-net/debris system. Simulations under tether tensioning conditions demonstrate the effectiveness of the closure concept for debris containment, in the gravity-free environment of space, for a realistic debris target. The on-ground experimental test-bed is also used to showcase its utility for validating the dynamics simulation of the net deployment, and a full-scale automated setup would make possible a range of validation studies of other aspects of a tether-net debris capture mission.

Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks

Science.gov (United States)

Sun, Bo; Cao, Siming; He, Jun; Yu, Lejun; Li, Liandong

2017-03-01

Constrained by the physiology, the temporal factors associated with human behavior, irrespective of facial movement or body gesture, are described by four phases: neutral, onset, apex, and offset. Although they may benefit related recognition tasks, it is not easy to accurately detect such temporal segments. An automatic temporal segment detection framework using bilateral long short-term memory recurrent neural networks (BLSTM-RNN) to learn high-level temporal-spatial features, which synthesizes the local and global temporal-spatial information more efficiently, is presented. The framework is evaluated in detail over the face and body database (FABO). The comparison shows that the proposed framework outperforms state-of-the-art methods for solving the problem of temporal segment detection.

A patch-based convolutional neural network for remote sensing image classification.

Science.gov (United States)

Sharma, Atharva; Liu, Xiuwen; Yang, Xiaojun; Shi, Di

2017-11-01

Availability of accurate land cover information over large areas is essential to the global environment sustainability; digital classification using medium-resolution remote sensing data would provide an effective method to generate the required land cover information. However, low accuracy of existing per-pixel based classification methods for medium-resolution data is a fundamental limiting factor. While convolutional neural networks (CNNs) with deep layers have achieved unprecedented improvements in object recognition applications that rely on fine image structures, they cannot be applied directly to medium-resolution data due to lack of such fine structures. In this paper, considering the spatial relation of a pixel to its neighborhood, we propose a new deep patch-based CNN system tailored for medium-resolution remote sensing data. The system is designed by incorporating distinctive characteristics of medium-resolution data; in particular, the system computes patch-based samples from multidimensional top of atmosphere reflectance data. With a test site from the Florida Everglades area (with a size of 771 square kilometers), the proposed new system has outperformed pixel-based neural network, pixel-based CNN and patch-based neural network by 24.36%, 24.23% and 11.52%, respectively, in overall classification accuracy. By combining the proposed deep CNN and the huge collection of medium-resolution remote sensing data, we believe that much more accurate land cover datasets can be produced over large areas. Copyright © 2017 Elsevier Ltd. All rights reserved.

Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data.

Science.gov (United States)

Koutsoukas, Alexios; Monaghan, Keith J; Li, Xiaoli; Huan, Jun

2017-06-28

In recent years, research in artificial neural networks has resurged, now under the deep-learning umbrella, and grown extremely popular. Recently reported success of DL techniques in crowd-sourced QSAR and predictive toxicology competitions has showcased these methods as powerful tools in drug-discovery and toxicology research. The aim of this work was dual, first large number of hyper-parameter configurations were explored to investigate how they affect the performance of DNNs and could act as starting points when tuning DNNs and second their performance was compared to popular methods widely employed in the field of cheminformatics namely Naïve Bayes, k-nearest neighbor, random forest and support vector machines. Moreover, robustness of machine learning methods to different levels of artificially introduced noise was assessed. The open-source Caffe deep-learning framework and modern NVidia GPU units were utilized to carry out this study, allowing large number of DNN configurations to be explored. We show that feed-forward deep neural networks are capable of achieving strong classification performance and outperform shallow methods across diverse activity classes when optimized. Hyper-parameters that were found to play critical role are the activation function, dropout regularization, number hidden layers and number of neurons. When compared to the rest methods, tuned DNNs were found to statistically outperform, with p value <0.01 based on Wilcoxon statistical test. DNN achieved on average MCC units of 0.149 higher than NB, 0.092 than kNN, 0.052 than SVM with linear kernel, 0.021 than RF and finally 0.009 higher than SVM with radial basis function kernel. When exploring robustness to noise, non-linear methods were found to perform well when dealing with low levels of noise, lower than or equal to 20%, however when dealing with higher levels of noise, higher than 30%, the Naïve Bayes method was found to perform well and even outperform at the highest level of

On the improvement of neural cryptography using erroneous transmitted information with error prediction.

Science.gov (United States)

Allam, Ahmed M; Abbas, Hazem M

2010-12-01

Neural cryptography deals with the problem of "key exchange" between two neural networks using the mutual learning concept. The two networks exchange their outputs (in bits) and the key between the two communicating parties is eventually represented in the final learned weights, when the two networks are said to be synchronized. Security of neural synchronization is put at risk if an attacker is capable of synchronizing with any of the two parties during the training process. Therefore, diminishing the probability of such a threat improves the reliability of exchanging the output bits through a public channel. The synchronization with feedback algorithm is one of the existing algorithms that enhances the security of neural cryptography. This paper proposes three new algorithms to enhance the mutual learning process. They mainly depend on disrupting the attacker confidence in the exchanged outputs and input patterns during training. The first algorithm is called "Do not Trust My Partner" (DTMP), which relies on one party sending erroneous output bits, with the other party being capable of predicting and correcting this error. The second algorithm is called "Synchronization with Common Secret Feedback" (SCSFB), where inputs are kept partially secret and the attacker has to train its network on input patterns that are different from the training sets used by the communicating parties. The third algorithm is a hybrid technique combining the features of the DTMP and SCSFB. The proposed approaches are shown to outperform the synchronization with feedback algorithm in the time needed for the parties to synchronize.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation

Science.gov (United States)

Camuñas-Mesa, Luis A.; Domínguez-Cordero, Yaisel L.; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network. PMID:29515349

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation

Directory of Open Access Journals (Sweden)

Luis A. Camuñas-Mesa

2018-02-01

Full Text Available Convolutional Neural Networks (ConvNets are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation.

Science.gov (United States)

Camuñas-Mesa, Luis A; Domínguez-Cordero, Yaisel L; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network.

The Elementary Nature of Purposive Behavior: Evolving Minimal Neural Structures that Display Intrinsic Intentionality

Directory of Open Access Journals (Sweden)

John S. Watson

2005-01-01

Full Text Available A study of the evolution of agency in artificial life was designed to access the potential emergence of purposiveness and intentionality as these attributes of behavior have been defined in psychology and philosophy. The study involved Darwinian evolution of mobile neural nets (autonomous agents in terms of their adaptive weight patterning and structure (number of sensory, hidden, and memory units that controlled movement. An agent was embedded in a 10 × 10 toroidal matrix along with “containers” that held benefit or harm if entered. Sensory exposure to content of a container was only briefly available at a distance so that adaptive response to a nearby container required use of relevant memory. The best 20% of each generation of agents, based on net benefit consumed during limited lifetime, were selected to parent the following generation. Purposiveness emerged for all selected agents by 300 generations. By 4000 generations, 90% passed a test of purposive intentionality based on Piaget's criteria for Stage IV object permanence in human infants. An additional test of these agents confirmed that the behavior of 67% of them was consistent with the philosophical criterion of intention being “about” the container's contents. Given that the evolved neural structure of more than half of the successful agents had only 1 hidden and 1 memory node, it is argued that, contrary to common assumption, purposive and intentional aspects of adaptive behavior require an evolution of minimal complexity of supportive neural structure.

[The Identification of the Origin of Chinese Wolfberry Based on Infrared Spectral Technology and the Artificial Neural Network].

Science.gov (United States)

Li, Zhong; Liu, Ming-de; Ji, Shou-xiang

2016-03-01

The Fourier Transform Infrared Spectroscopy (FTIR) is established to find the geographic origins of Chinese wolfberry quickly. In the paper, the 45 samples of Chinese wolfberry from different places of Qinghai Province are to be surveyed by FTIR. The original data matrix of FTIR is pretreated with common preprocessing and wavelet transform. Compared with common windows shifting smoothing preprocessing, standard normal variation correction and multiplicative scatter correction, wavelet transform is an effective spectrum data preprocessing method. Before establishing model through the artificial neural networks, the spectra variables are compressed by means of the wavelet transformation so as to enhance the training speed of the artificial neural networks, and at the same time the related parameters of the artificial neural networks model are also discussed in detail. The survey shows even if the infrared spectroscopy data is compressed to 1/8 of its original data, the spectral information and analytical accuracy are not deteriorated. The compressed spectra variables are used for modeling parameters of the backpropagation artificial neural network (BP-ANN) model and the geographic origins of Chinese wolfberry are used for parameters of export. Three layers of neural network model are built to predict the 10 unknown samples by using the MATLAB neural network toolbox design error back propagation network. The number of hidden layer neurons is 5, and the number of output layer neuron is 1. The transfer function of hidden layer is tansig, while the transfer function of output layer is purelin. Network training function is trainl and the learning function of weights and thresholds is learngdm. net. trainParam. epochs=1 000, while net. trainParam. goal = 0.001. The recognition rate of 100% is to be achieved. It can be concluded that the method is quite suitable for the quick discrimination of producing areas of Chinese wolfberry. The infrared spectral analysis technology

ROOT.NET: Using ROOT from .NET languages like C# and F#

Science.gov (United States)

Watts, G.

2012-12-01

ROOT.NET provides an interface between Microsoft's Common Language Runtime (CLR) and .NET technology and the ubiquitous particle physics analysis tool, ROOT. ROOT.NET automatically generates a series of efficient wrappers around the ROOT API. Unlike pyROOT, these wrappers are statically typed and so are highly efficient as compared to the Python wrappers. The connection to .NET means that one gains access to the full series of languages developed for the CLR including functional languages like F# (based on OCaml). Many features that make ROOT objects work well in the .NET world are added (properties, IEnumerable interface, LINQ compatibility, etc.). Dynamic languages based on the CLR can be used as well, of course (Python, for example). Additionally it is now possible to access ROOT objects that are unknown to the translation tool. This poster will describe the techniques used to effect this translation, along with performance comparisons, and examples. All described source code is posted on the open source site CodePlex.

ROOT.NET: Using ROOT from .NET languages like C and F

International Nuclear Information System (INIS)

Watts, G

2012-01-01

ROOT.NET provides an interface between Microsoft's Common Language Runtime (CLR) and .NET technology and the ubiquitous particle physics analysis tool, ROOT. ROOT.NET automatically generates a series of efficient wrappers around the ROOT API. Unlike pyROOT, these wrappers are statically typed and so are highly efficient as compared to the Python wrappers. The connection to .NET means that one gains access to the full series of languages developed for the CLR including functional languages like F (based on OCaml). Many features that make ROOT objects work well in the .NET world are added (properties, IEnumerable interface, LINQ compatibility, etc.). Dynamic languages based on the CLR can be used as well, of course (Python, for example). Additionally it is now possible to access ROOT objects that are unknown to the translation tool. This poster will describe the techniques used to effect this translation, along with performance comparisons, and examples. All described source code is posted on the open source site CodePlex.

Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection

Directory of Open Access Journals (Sweden)

Erik Marchi

2017-01-01

Full Text Available In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F-measure over the three databases.

Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection.

Science.gov (United States)

Marchi, Erik; Vesperini, Fabio; Squartini, Stefano; Schuller, Björn

2017-01-01

In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F -measure over the three databases.

Study of the Gray Scale, Polychromatic, Distortion Invariant Neural Networks Using the Ipa Model.

Science.gov (United States)

Uang, Chii-Maw

Research in the optical neural network field is primarily motivated by the fact that humans recognize objects better than the conventional digital computers and the massively parallel inherent nature of optics. This research represents a continuous effort during the past several years in the exploitation of using neurocomputing for pattern recognition. Based on the interpattern association (IPA) model and Hamming net model, many new systems and applications are introduced. A gray level discrete associative memory that is based on object decomposition/composition is proposed for recognizing gray-level patterns. This technique extends the processing ability from the binary mode to gray-level mode, and thus the information capacity is increased. Two polychromatic optical neural networks using color liquid crystal television (LCTV) panels for color pattern recognition are introduced. By introducing a color encoding technique in conjunction with the interpattern associative algorithm, a color associative memory was realized. Based on the color decomposition and composition technique, a color exemplar-based Hamming net was built for color image classification. A shift-invariant neural network is presented through use of the translation invariant property of the modulus of the Fourier transformation and the hetero-associative interpattern association (IPA) memory. To extract the main features, a quadrantal sampling method is used to sampled data and then replace the training patterns. Using the concept of hetero-associative memory to recall the distorted object. A shift and rotation invariant neural network using an interpattern hetero-association (IHA) model is presented. To preserve the shift and rotation invariant properties, a set of binarized-encoded circular harmonic expansion (CHE) functions at the Fourier domain is used as the training set. We use the shift and symmetric properties of the modulus of the Fourier spectrum to avoid the problem of centering the CHE

Neural network AE source location apart from structure size and material

Czech Academy of Sciences Publication Activity Database

Chlada, Milan; Převorovský, Zdeněk; Blaháček, Michal

2010-01-01

Roč. 28, - (2010), s. 99-107 ISSN 0730-0050. [European Conference on Acoustic Emission Testing 2010 /29./. Vídeň, 08.09.2010-10.09.2010] R&D Projects: GA ČR(CZ) GAP104/10/1430; GA MPO(CZ) FR-TI1/274 Institutional research plan: CEZ:AV0Z20760514 Keywords : AE source location * artificial neural network * arrival time profiles Subject RIV: BI - Acoustics http://www.ndt.net/search/abstract.php3?AbsID=10828

Models of neural networks temporal aspects of coding and information processing in biological systems

CERN Document Server

Hemmen, J; Schulten, Klaus

1994-01-01

Since the appearance of Vol. 1 of Models of Neural Networks in 1991, the theory of neural nets has focused on two paradigms: information coding through coherent firing of the neurons and functional feedback. Information coding through coherent neuronal firing exploits time as a cardinal degree of freedom. This capacity of a neural network rests on the fact that the neuronal action potential is a short, say 1 ms, spike, localized in space and time. Spatial as well as temporal correlations of activity may represent different states of a network. In particular, temporal correlations of activity may express that neurons process the same "object" of, for example, a visual scene by spiking at the very same time. The traditional description of a neural network through a firing rate, the famous S-shaped curve, presupposes a wide time window of, say, at least 100 ms. It thus fails to exploit the capacity to "bind" sets of coherently firing neurons for the purpose of both scene segmentation and figure-ground segregatio...

Sensory Gain Outperforms Efficient Readout Mechanisms in Predicting Attention-Related Improvements in Behavior

Science.gov (United States)

Ester, Edward F.; Deering, Sean

2014-01-01

Spatial attention has been postulated to facilitate perceptual processing via several different mechanisms. For instance, attention can amplify neural responses in sensory areas (sensory gain), mediate neural variability (noise modulation), or alter the manner in which sensory signals are selectively read out by postsensory decision mechanisms (efficient readout). Even in the context of simple behavioral tasks, it is unclear how well each of these mechanisms can account for the relationship between attention-modulated changes in behavior and neural activity because few studies have systematically mapped changes between stimulus intensity, attentional focus, neural activity, and behavioral performance. Here, we used a combination of psychophysics, event-related potentials (ERPs), and quantitative modeling to explicitly link attention-related changes in perceptual sensitivity with changes in the ERP amplitudes recorded from human observers. Spatial attention led to a multiplicative increase in the amplitude of an early sensory ERP component (the P1, peaking ∼80–130 ms poststimulus) and in the amplitude of the late positive deflection component (peaking ∼230–330 ms poststimulus). A simple model based on signal detection theory demonstrates that these multiplicative gain changes were sufficient to account for attention-related improvements in perceptual sensitivity, without a need to invoke noise modulation. Moreover, combining the observed multiplicative gain with a postsensory readout mechanism resulted in a significantly poorer description of the observed behavioral data. We conclude that, at least in the context of relatively simple visual discrimination tasks, spatial attention modulates perceptual sensitivity primarily by modulating the gain of neural responses during early sensory processing PMID:25274817

A Green Energy Application in Energy Management Systems by an Artificial Intelligence-Based Solar Radiation Forecasting Model

Directory of Open Access Journals (Sweden)

Ping-Huan Kuo

2018-04-01

Full Text Available The photovoltaic (PV systems generate green energy from the sunlight without any pollution or noise. The PV systems are simple, convenient to install, and seldom malfunction. Unfortunately, the energy generated by PV systems depends on climatic conditions, location, and system design. The solar radiation forecasting is important to the smooth operation of PV systems. However, solar radiation detected by a pyranometer sensor is strongly nonlinear and highly unstable. The PV energy generation makes a considerable contribution to the smart grids via a large number of relatively small PV systems. In this paper, a high-precision deep convolutional neural network model (SolarNet is proposed to facilitate the solar radiation forecasting. The proposed model is verified by experiments. The experimental results demonstrate that SolarNet outperforms other benchmark models in forecasting accuracy as well as in predicting complex time series with a high degree of volatility and irregularity.

INMARSAT-C SafetyNET

Science.gov (United States)

Tsunamis 406 EPIRB's National Weather Service Marine Forecasts INMARSAT-C SafetyNET Marine Forecast Offices greater danger near shore or any shallow waters? NATIONAL WEATHER SERVICE PRODUCTS VIA INMARSAT-C SafetyNET Inmarsat-C SafetyNET is an internationally adopted, automated satellite system for promulgating

Efficient Embedded Decoding of Neural Network Language Models in a Machine Translation System.

Science.gov (United States)

Zamora-Martinez, Francisco; Castro-Bleda, Maria Jose

2018-02-22

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks

Directory of Open Access Journals (Sweden)

Liang Chen

2017-01-01

Full Text Available Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs: one is an ensemble of two DeconvNets (Noh et al., 2015, which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net, which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks.

Science.gov (United States)

Chen, Liang; Bentley, Paul; Rueckert, Daniel

2017-01-01

Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

Generating Seismograms with Deep Neural Networks

Science.gov (United States)

Krischer, L.; Fichtner, A.

2017-12-01

The recent surge of successful uses of deep neural networks in computer vision, speech recognition, and natural language processing, mainly enabled by the availability of fast GPUs and extremely large data sets, is starting to see many applications across all natural sciences. In seismology these are largely confined to classification and discrimination tasks. In this contribution we explore the use of deep neural networks for another class of problems: so called generative models.Generative modelling is a branch of statistics concerned with generating new observed data samples, usually by drawing from some underlying probability distribution. Samples with specific attributes can be generated by conditioning on input variables. In this work we condition on seismic source (mechanism and location) and receiver (location) parameters to generate multi-component seismograms.The deep neural networks are trained on synthetic data calculated with Instaseis (http://instaseis.net, van Driel et al. (2015)) and waveforms from the global ShakeMovie project (http://global.shakemovie.princeton.edu, Tromp et al. (2010)). The underlying radially symmetric or smoothly three dimensional Earth structures result in comparatively small waveform differences from similar events or at close receivers and the networks learn to interpolate between training data samples.Of particular importance is the chosen misfit functional. Generative adversarial networks (Goodfellow et al. (2014)) implement a system in which two networks compete: the generator network creates samples and the discriminator network distinguishes these from the true training examples. Both are trained in an adversarial fashion until the discriminator can no longer distinguish between generated and real samples. We show how this can be applied to seismograms and in particular how it compares to networks trained with more conventional misfit metrics. Last but not least we attempt to shed some light on the black-box nature of

Quantum net dynamics

International Nuclear Information System (INIS)

Finkelstein, D.

1989-01-01

The quantum net unifies the basic principles of quantum theory and relativity in a quantum spacetime having no ultraviolet infinities, supporting the Dirac equation, and having the usual vacuum as a quantum condensation. A correspondence principle connects nets to Schwinger sources and further unifies the vertical structure of the theory, so that the functions of the many hierarchic levels of quantum field theory (predicate algebra, set theory, topology,hor-ellipsis, quantum dynamics) are served by one in quantum net dynamics

HAWC Analysis of the Crab Nebula Using Neural-Net Energy Reconstruction

Science.gov (United States)

Marinelli, Samuel; HAWC Collaboration

2017-01-01

The HAWC (High-Altitude Water-Cherenkov) experiment is a TeV γ-ray observatory located 4100 m above sea level on the Sierra Negra mountain in Puebla, Mexico. The detector consists of 300 water-filled tanks, each instrumented with 4 photomuliplier tubes that utilize the water-Cherenkov technique to detect atmospheric air showers produced by cosmic γ rays. Construction of HAWC was completed in March, 2015. The experiment's wide field of view (2 sr) and high duty cycle (> 95 %) make it a powerful survey instrument sensitive to pulsar wind nebulae, supernova remnants, active galactic nuclei, and other γ-ray sources. The mechanisms of particle acceleration at these sources can be studied by analyzing their energy spectra. To this end, we have developed an event-by-event energy-reconstruction algorithm employing an artificial neural network to estimate energies of primary γ rays. The Crab Nebula, the brightest source of TeV photons, makes an excellent calibration source for this technique. We will present preliminary results from an analysis of the Crab energy spectrum using this new energy-reconstruction method. This work was supported by the National Science Foundation.

High-level Petri Nets

DEFF Research Database (Denmark)

various journals and collections. As a result, much of this knowledge is not readily available to people who may be interested in using high-level nets. Within the Petri net community this problem has been discussed many times, and as an outcome this book has been compiled. The book contains reprints...... of some of the most important papers on the application and theory of high-level Petri nets. In this way it makes the relevant literature more available. It is our hope that the book will be a useful source of information and that, e.g., it can be used in the organization of Petri net courses. To make......High-level Petri nets are now widely used in both theoretical analysis and practical modelling of concurrent systems. The main reason for the success of this class of net models is that they make it possible to obtain much more succinct and manageable descriptions than can be obtained by means...

An effective convolutional neural network model for Chinese sentiment analysis

Science.gov (United States)

Zhang, Yu; Chen, Mengdong; Liu, Lianzhong; Wang, Yadong

2017-06-01

Nowadays microblog is getting more and more popular. People are increasingly accustomed to expressing their opinions on Twitter, Facebook and Sina Weibo. Sentiment analysis of microblog has received significant attention, both in academia and in industry. So far, Chinese microblog exploration still needs lots of further work. In recent years CNN has also been used to deal with NLP tasks, and already achieved good results. However, these methods ignore the effective use of a large number of existing sentimental resources. For this purpose, we propose a Lexicon-based Sentiment Convolutional Neural Networks (LSCNN) model focus on Weibo's sentiment analysis, which combines two CNNs, trained individually base on sentiment features and word embedding, at the fully connected hidden layer. The experimental results show that our model outperforms the CNN model only with word embedding features on microblog sentiment analysis task.

Prediction of net energy consumption based on economic indicators (GNP and GDP) in Turkey

International Nuclear Information System (INIS)

Soezen, Adnan; Arcaklioglu, Erol

2007-01-01

The most important theme in this study is to obtain equations based on economic indicators (gross national product-GNP and gross domestic product-GDP) and population increase to predict the net energy consumption of Turkey using artificial neural networks (ANNs) in order to determine future level of the energy consumption and make correct investments in Turkey. In this study, three different models were used in order to train the ANN. In one of them (Model 1), energy indicators such as installed capacity, generation, energy import and energy export, in second (Model 2), GNP was used and in the third (Model 3), GDP was used as the input layer of the network. The net energy consumption (NEC) is in the output layer for all models. In order to train the neural network, economic and energy data for last 37 years (1968-2005) are used in network for all models. The aim of used different models is to demonstrate the effect of economic indicators on the estimation of NEC. The maximum mean absolute percentage error (MAPE) was found to be 2.322732, 1.110525 and 1.122048 for Models 1, 2 and 3, respectively. R 2 values were obtained as 0.999444, 0.999903 and 0.999903 for training data of Models 1, 2 and 3, respectively. The ANN approach shows greater accuracy for evaluating NEC based on economic indicators. Based on the outputs of the study, the ANN model can be used to estimate the NEC from the country's population and economic indicators with high confidence for planing future projections

Artificial neural network model of pork meat cubes osmotic dehydration

OpenAIRE

Pezo, Lato L.; Ćurčić, Biljana Lj.; Filipović, Vladimir S.; Nićetin, Milica R.; Koprivica, Gordana B.; Mišljenović, Nevena M.; Lević, Ljubinko B.

2013-01-01

Mass transfer of pork meat cubes (M. triceps brachii), shaped as 1x1x1 cm, during osmotic dehydration (OD) and under atmospheric pressure was investigated in this paper. The effects of different parameters, such as concentration of sugar beet molasses (60-80%, w/w), temperature (20-50ºC), and immersion time (1-5 h) in terms of water loss (WL), solid gain (SG), final dry matter content (DM), and water activity (aw), were investigated using experimental results. Five artificial neural net...

Applying deep neural networks to HEP job classification

International Nuclear Information System (INIS)

Wang, L; Shi, J; Yan, X

2015-01-01

The cluster of IHEP computing center is a middle-sized computing system which provides 10 thousands CPU cores, 5 PB disk storage, and 40 GB/s IO throughput. Its 1000+ users come from a variety of HEP experiments. In such a system, job classification is an indispensable task. Although experienced administrator can classify a HEP job by its IO pattern, it is unpractical to classify millions of jobs manually. We present how to solve this problem with deep neural networks in a supervised learning way. Firstly, we built a training data set of 320K samples by an IO pattern collection agent and a semi-automatic process of sample labelling. Then we implemented and trained DNNs models with Torch. During the process of model training, several meta-parameters was tuned with cross-validations. Test results show that a 5- hidden-layer DNNs model achieves 96% precision on the classification task. By comparison, it outperforms a linear model by 8% precision. (paper)

Probabilistic models for neural populations that naturally capture global coupling and criticality.

Science.gov (United States)

Humplik, Jan; Tkačik, Gašper

2017-09-01

Advances in multi-unit recordings pave the way for statistical modeling of activity patterns in large neural populations. Recent studies have shown that the summed activity of all neurons strongly shapes the population response. A separate recent finding has been that neural populations also exhibit criticality, an anomalously large dynamic range for the probabilities of different population activity patterns. Motivated by these two observations, we introduce a class of probabilistic models which takes into account the prior knowledge that the neural population could be globally coupled and close to critical. These models consist of an energy function which parametrizes interactions between small groups of neurons, and an arbitrary positive, strictly increasing, and twice differentiable function which maps the energy of a population pattern to its probability. We show that: 1) augmenting a pairwise Ising model with a nonlinearity yields an accurate description of the activity of retinal ganglion cells which outperforms previous models based on the summed activity of neurons; 2) prior knowledge that the population is critical translates to prior expectations about the shape of the nonlinearity; 3) the nonlinearity admits an interpretation in terms of a continuous latent variable globally coupling the system whose distribution we can infer from data. Our method is independent of the underlying system's state space; hence, it can be applied to other systems such as natural scenes or amino acid sequences of proteins which are also known to exhibit criticality.

Construction of Neural Networks for Realization of Localized Deep Learning

Directory of Open Access Journals (Sweden)

Charles K. Chui

2018-05-01

Full Text Available The subject of deep learning has recently attracted users of machine learning from various disciplines, including: medical diagnosis and bioinformatics, financial market analysis and online advertisement, speech and handwriting recognition, computer vision and natural language processing, time series forecasting, and search engines. However, theoretical development of deep learning is still at its infancy. The objective of this paper is to introduce a deep neural network (also called deep-net approach to localized manifold learning, with each hidden layer endowed with a specific learning task. For the purpose of illustrations, we only focus on deep-nets with three hidden layers, with the first layer for dimensionality reduction, the second layer for bias reduction, and the third layer for variance reduction. A feedback component is also designed to deal with outliers. The main theoretical result in this paper is the order O(m-2s/(2s+d of approximation of the regression function with regularity s, in terms of the number m of sample points, where the (unknown manifold dimension d replaces the dimension D of the sampling (Euclidean space for shallow nets.

Bone age detection via carpogram analysis using convolutional neural networks

Science.gov (United States)

Torres, Felipe; Bravo, María. Alejandra; Salinas, Emmanuel; Triana, Gustavo; Arbeláez, Pablo

2017-11-01

Bone age assessment is a critical factor for determining delayed development in children, which can be a sign of pathologies such as endocrine diseases, growth abnormalities, chromosomal, neurological and congenital disorders among others. In this paper we present BoneNet, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks. We train and evaluate our algorithm on a database of X-Ray images provided by the hospital Fundacion Santa Fe de Bogot ´ a with around 1500 images of patients between the ages 1 to 18. ´ We compare two different architectures to classify the given data in order to explore the generality of our method. To accomplish this, we define multiple binary age assessment problems, dividing the data by bone age and differentiating the patients by their gender. Thus, exploring several parameters, we develop BoneNet. Our approach is holistic, efficient, and modular, since it is possible for the specialists to use all the networks combined to determine how is the skeletal maturity of a patient. BoneNet achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age.

Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode

Directory of Open Access Journals (Sweden)

Tao Ye

2018-06-01

Full Text Available Many accidents happen under shunting mode when the speed of a train is below 45 km/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net. It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 × 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.

Planning of nets

International Nuclear Information System (INIS)

Carberry, M

1996-01-01

The paper is about the planning of nets in areas of low density like it is the case of the rural areas. The author includes economic and technological aspects, planning of nets, demands and management among others

A novel neural-net-based nonlinear adaptive control and application to the cross-direction deviations control of a polymer film spread line

International Nuclear Information System (INIS)

Chen Zengqiang; Li Xiang; Liu Zhongxin; Yuan Zhuzhi

2008-01-01

A novel neural adaptive controller is presented to effectively control multivariable nonlinear systems. The proposed neural controller has been successfully applied to the cross-direction deviation control system of a polymer film spread line, whose good performance has been verified with real-time running results

Programming NET Web Services

CERN Document Server

Ferrara, Alex

2007-01-01

Web services are poised to become a key technology for a wide range of Internet-enabled applications, spanning everything from straight B2B systems to mobile devices and proprietary in-house software. While there are several tools and platforms that can be used for building web services, developers are finding a powerful tool in Microsoft's .NET Framework and Visual Studio .NET. Designed from scratch to support the development of web services, the .NET Framework simplifies the process--programmers find that tasks that took an hour using the SOAP Toolkit take just minutes. Programming .NET

Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network

International Nuclear Information System (INIS)

Zeng, Yu-Rong; Zeng, Yi; Choi, Beomjin; Wang, Lin

2017-01-01

Reliable energy consumption forecasting can provide effective decision-making support for planning development strategies to energy enterprises and for establishing national energy policies. Accordingly, the present study aims to apply a hybrid intelligent approach named ADE–BPNN, the back-propagation neural network (BPNN) model supported by an adaptive differential evolution algorithm, to estimate energy consumption. Most often, energy consumption is influenced by socioeconomic factors. The proposed hybrid model incorporates gross domestic product, population, import, and export data as inputs. An improved differential evolution with adaptive mutation and crossover is utilized to find appropriate global initial connection weights and thresholds to enhance the forecasting performance of the BPNN. A comparative example and two extended examples are utilized to validate the applicability and accuracy of the proposed ADE–BPNN model. Errors of the test data sets indicate that the ADE–BPNN model can effectively predict energy consumption compared with the traditional back-propagation neural network model and other popular existing models. Moreover, mean impact value based analysis is conducted for electrical energy consumption in U.S. and total energy consumption forecasting in China to quantitatively explore the relative importance of each input variable for the improvement of effective energy consumption prediction. - Highlights: • Enhanced back-propagation neural network (ADE-BPNN) for energy consumption forecasting. • ADE-BPNN outperforms the current best models for two comparative cases. • Mean impact value approach explores socio-economic factors' relative importance. • ADE-BPNN's adjusted goodness-of-fit is 99.2% for China's energy consumption forecasting.

Game Coloured Petri Nets

DEFF Research Database (Denmark)

Westergaard, Michael

2006-01-01

This paper introduces the notion of game coloured Petri nets. This allows the modeler to explicitly model what parts of the model comprise the modeled system and what parts are the environment of the modeled system. We give the formal definition of game coloured Petri nets, a means of reachability...... analysis of this net class, and an application of game coloured Petri nets to automatically generate easy-to-understand visualizations of the model by exploiting the knowledge that some parts of the model are not interesting from a visualization perspective (i.e. they are part of the environment...

Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network.

Science.gov (United States)

Du, Xiaofeng; Qu, Xiaobo; He, Yifan; Guo, Di

2018-03-06

Deep convolutional neural networks (CNNs) are successful in single-image super-resolution. Traditional CNNs are limited to exploit multi-scale contextual information for image reconstruction due to the fixed convolutional kernel in their building modules. To restore various scales of image details, we enhance the multi-scale inference capability of CNNs by introducing competition among multi-scale convolutional filters, and build up a shallow network under limited computational resources. The proposed network has the following two advantages: (1) the multi-scale convolutional kernel provides the multi-context for image super-resolution, and (2) the maximum competitive strategy adaptively chooses the optimal scale of information for image reconstruction. Our experimental results on image super-resolution show that the performance of the proposed network outperforms the state-of-the-art methods.

A Pilot Study of Biomedical Text Comprehension using an Attention-Based Deep Neural Reader: Design and Experimental Analysis.

Science.gov (United States)

Kim, Seongsoon; Park, Donghyeon; Choi, Yonghwa; Lee, Kyubum; Kim, Byounggun; Jeon, Minji; Kim, Jihye; Tan, Aik Choon; Kang, Jaewoo

2018-01-05

With the development of artificial intelligence (AI) technology centered on deep-learning, the computer has evolved to a point where it can read a given text and answer a question based on the context of the text. Such a specific task is known as the task of machine comprehension. Existing machine comprehension tasks mostly use datasets of general texts, such as news articles or elementary school-level storybooks. However, no attempt has been made to determine whether an up-to-date deep learning-based machine comprehension model can also process scientific literature containing expert-level knowledge, especially in the biomedical domain. This study aims to investigate whether a machine comprehension model can process biomedical articles as well as general texts. Since there is no dataset for the biomedical literature comprehension task, our work includes generating a large-scale question answering dataset using PubMed and manually evaluating the generated dataset. We present an attention-based deep neural model tailored to the biomedical domain. To further enhance the performance of our model, we used a pretrained word vector and biomedical entity type embedding. We also developed an ensemble method of combining the results of several independent models to reduce the variance of the answers from the models. The experimental results showed that our proposed deep neural network model outperformed the baseline model by more than 7% on the new dataset. We also evaluated human performance on the new dataset. The human evaluation result showed that our deep neural model outperformed humans in comprehension by 22% on average. In this work, we introduced a new task of machine comprehension in the biomedical domain using a deep neural model. Since there was no large-scale dataset for training deep neural models in the biomedical domain, we created the new cloze-style datasets Biomedical Knowledge Comprehension Title (BMKC_T) and Biomedical Knowledge Comprehension Last

Coloured Petri Nets

DEFF Research Database (Denmark)

Jensen, Kurt

1991-01-01

This paper describes how Coloured Petri Nets (CP-nets) have been developed — from being a promising theoretical model to being a full-fledged language for the design, specification, simulation, validation and implementation of large software systems (and other systems in which human beings and...

Net zero water

CSIR Research Space (South Africa)

Lindeque, M

2013-01-01

Full Text Available the national grid. The unfortunate situation with water is that there is no replacement technology for water. Water can be supplied from many different sources. A net zero energy development will move closer to a net zero water development by reducing...

Statistical physics, neural networks, brain studies

International Nuclear Information System (INIS)

Toulouse, G.

1999-01-01

An overview of some aspects of a vast domain, located at the crossroads of physics, biology and computer science is presented: (1) During the last fifteen years, physicists advancing along various pathways have come into contact with biology (computational neurosciences) and engineering (formal neural nets). (2) This move may actually be viewed as one component in a larger picture. A prominent trend of recent years, observable over many countries, has been the establishment of interdisciplinary centers devoted to the study of: cognitive sciences; natural and artificial intelligence; brain, mind and behaviour; perception and action; learning and memory; robotics; man-machine communication, etc. What are the promising lines of development? What opportunities for physicists? An attempt will be made to address such questions and related issues

Study on the identifying of meat's visible spectrum based on BP artificial neural network

Science.gov (United States)

Li, Xiaotian; Zhang, Tieqiang; Li, Bo; Jiang, Yongheng; Liu, Binghui; Li, Zhaokai

2006-01-01

A method to identify different meat by the visible and reflected spectra of meat with BP artificial neural net (BP-ANN) was introduced in this paper. The visible and reflected spectra (from 420 to 535nm) of different meat (beef and pork) were measured with fiber sensor spectrometer. A kind of ANN with a double-hidden layer was created to identify the different meat automatically. Its right ratio reaches 92.71%.

Towards new information resources for public health--from WordNet to MedicalWordNet.

Science.gov (United States)

Fellbaum, Christiane; Hahn, Udo; Smith, Barry

2006-06-01

In the last two decades, WordNet has evolved as the most comprehensive computational lexicon of general English. In this article, we discuss its potential for supporting the creation of an entirely new kind of information resource for public health, viz. MedicalWordNet. This resource is not to be conceived merely as a lexical extension of the original WordNet to medical terminology; indeed, there is already a considerable degree of overlap between WordNet and the vocabulary of medicine. Instead, we propose a new type of repository, consisting of three large collections of (1) medically relevant word forms, structured along the lines of the existing Princeton WordNet; (2) medically validated propositions, referred to here as medical facts, which will constitute what we shall call MedicalFactNet; and (3) propositions reflecting laypersons' medical beliefs, which will constitute what we shall call the MedicalBeliefNet. We introduce a methodology for setting up the MedicalWordNet. We then turn to the discussion of research challenges that have to be met to build this new type of information resource. We build a database of sentences relevant to the medical domain. The sentences are generated from WordNet via its relations as well as from medical statements broken down into elementary propositions. Two subcorpora of sentences are distinguished, MedicalBeliefNet and MedicalFactNet. The former is rated for assent by laypersons; the latter for correctness by medical experts. The sentence corpora will be valuable for a variety of applications in information retrieval as well as in research in linguistics and psychology with respect to the study of expert and non-expert beliefs and their linguistic expressions. Our work has to meet several considerable challenges. These include accounting for the distinction between medical experts and laypersons, the social issues of expert-layperson communication in different media, the linguistic aspects of encoding medical knowledge, and

Construction of a Piezoresistive Neural Sensor Array

Science.gov (United States)

Carlson, W. B.; Schulze, W. A.; Pilgrim, P. M.

1996-01-01

The construction of a piezoresistive - piezoelectric sensor (or actuator) array is proposed using 'neural' connectivity for signal recognition and possible actuation functions. A closer integration of the sensor and decision functions is necessary in order to achieve intrinsic identification within the sensor. A neural sensor is the next logical step in development of truly 'intelligent' arrays. This proposal will integrate 1-3 polymer piezoresistors and MLC electroceramic devices for applications involving acoustic identification. The 'intelligent' piezoresistor -piezoelectric system incorporates printed resistors, composite resistors, and a feedback for the resetting of resistances. A model of a design is proposed in order to simulate electromechanical resistor interactions. The goal of optimizing a sensor geometry for improving device reliability, training, & signal identification capabilities is the goal of this work. At present, studies predict performance of a 'smart' device with a significant control of 'effective' compliance over a narrow pressure range due to a piezoresistor percolation threshold. An interesting possibility may be to use an array of control elements to shift the threshold function in order to change the level of resistance in a neural sensor array for identification, or, actuation applications. The proposed design employs elements of: (1) conductor loaded polymers for a 'fast' RC time constant response; and (2) multilayer ceramics for actuation or sensing and shifting of resistance in the polymer. Other material possibilities also exist using magnetoresistive layered systems for shifting the resistance. It is proposed to use a neural net configuration to test and to help study the possible changes required in the materials design of these devices. Numerical design models utilize electromechanical elements, in conjunction with structural elements in order to simulate piezoresistively controlled actuators and changes in resistance of sensors

An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks.

Science.gov (United States)

Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen

2016-01-01

The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper.

Multiflavor string-net models

Science.gov (United States)

Lin, Chien-Hung

2017-05-01

We generalize the string-net construction to multiple flavors of strings, each of which is labeled by the elements of an Abelian group Gi. The same flavor of strings can branch, while different flavors of strings can cross one another and thus they form intersecting string nets. We systematically construct the exactly soluble lattice Hamiltonians and the ground-state wave functions for the intersecting string-net condensed phases. We analyze the braiding statistics of the low-energy quasiparticle excitations and find that our model can realize all the topological phases as the string-net model with group G =∏iGi . In this respect, our construction provides various ways of building lattice models which realize topological order G , corresponding to different partitions of G and thus different flavors of string nets. In fact, our construction concretely demonstrates the Künneth formula by constructing various lattice models with the same topological order. As an example, we construct the G =Z2×Z2×Z2 string-net model which realizes a non-Abelian topological phase by properly intersecting three copies of toric codes.

A new approach for visual identification of orange varieties using neural networks and metaheuristic algorithms

Directory of Open Access Journals (Sweden)

Sajad Sabzi

2018-03-01

Full Text Available Accurate classification of fruit varieties in processing factories and during post-harvesting applications is a challenge that has been widely studied. This paper presents a novel approach to automatic fruit identification applied to three common varieties of oranges (Citrus sinensis L., namely Bam, Payvandi and Thomson. A total of 300 color images were used for the experiments, 100 samples for each orange variety, which are publicly available. After segmentation, 263 parameters, including texture, color and shape features, were extracted from each sample using image processing. Among them, the 6 most effective features were automatically selected by using a hybrid approach consisting of an artificial neural network and particle swarm optimization algorithm (ANN-PSO. Then, three different classifiers were applied and compared: hybrid artificial neural network – artificial bee colony (ANN-ABC; hybrid artificial neural network – harmony search (ANN-HS; and k-nearest neighbors (kNN. The experimental results show that the hybrid approaches outperform the results of kNN. The average correct classification rate of ANN-HS was 94.28%, while ANN-ABS achieved 96.70% accuracy with the available data, contrasting with the 70.9% baseline accuracy of kNN. Thus, this new proposed methodology provides a fast and accurate way to classify multiple fruits varieties, which can be easily implemented in processing factories. The main contribution of this work is that the method can be directly adapted to other use cases, since the selection of the optimal features and the configuration of the neural network are performed automatically using metaheuristic algorithms.

Rare, but challenging tumors: NET

International Nuclear Information System (INIS)

Ivanova, D.; Balev, B.

2013-01-01

Full text: Introduction: Gastroenteropancreatic Neuroendocrine Tumors (GEP - NET) are a heterogeneous group of tumors with different locations and many different clinical, histological, and imaging performance. In a part of them a secretion of various organic substances is present. The morbidity of GEP - NET in the EU is growing, and this leads to increase the attention to them. What you will learn: Imaging methods used for localization and staging of GEP - NET, characteristics of the study’s protocols; Classification of GEP - NET; Demonstration of typical and atypical imaging features of GEP - NET in patients registered at the NET Center at University Hospital ‘St. Marina’, Varna; Features of metastatic NET, The role of imaging in the evaluation of treatment response and follow-up of the patients. Discussion: The image semiotics analysis is based on 19 cases of GEP - NET registered NET Center at University Hospital ‘St. Marina’. The main imaging method is multidetector CT (MDCT), and magnetic resonance imaging (MRI ) has advantages in the evaluation of liver lesions and the local prevalence of anorectal tumors. In patients with advanced disease and liver lesions the assessment of skeletal involvement (MRI/ nuclear medical method) is mandatory. The majority of GEP - NET have not any specific imaging findings. Therefore it is extremely important proper planning and conducting of the study (MDCT and MR enterography; accurate assessment phase of scanning, positive and negative contrast). Conclusion: GEP - NET is a major diagnostic challenge due to the absence of typical imaging characteristics and often an overlap with those of the tumors of different origin can be observed. Therefore, a good knowledge of clinical and imaging changes occurring at different locations is needed. MDCT is the basis for the diagnosis, staging and follow-up of these neoplasms

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.

Science.gov (United States)

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; Lecun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons.

Limitations of shallow nets approximation.

Science.gov (United States)

Lin, Shao-Bo

2017-10-01

In this paper, we aim at analyzing the approximation abilities of shallow networks in reproducing kernel Hilbert spaces (RKHSs). We prove that there is a probability measure such that the achievable lower bound for approximating by shallow nets can be realized for all functions in balls of reproducing kernel Hilbert space with high probability, which is different with the classical minimax approximation error estimates. This result together with the existing approximation results for deep nets shows the limitations for shallow nets and provides a theoretical explanation on why deep nets perform better than shallow nets. Copyright © 2017 Elsevier Ltd. All rights reserved.

Cascaded bidirectional recurrent neural networks for protein secondary structure prediction.

Science.gov (United States)

Chen, Jinmiao; Chaudhari, Narendra

2007-01-01

Protein secondary structure (PSS) prediction is an important topic in bioinformatics. Our study on a large set of non-homologous proteins shows that long-range interactions commonly exist and negatively affect PSS prediction. Besides, we also reveal strong correlations between secondary structure (SS) elements. In order to take into account the long-range interactions and SS-SS correlations, we propose a novel prediction system based on cascaded bidirectional recurrent neural network (BRNN). We compare the cascaded BRNN against another two BRNN architectures, namely the original BRNN architecture used for speech recognition as well as Pollastri's BRNN that was proposed for PSS prediction. Our cascaded BRNN achieves an overall three state accuracy Q3 of 74.38\\%, and reaches a high Segment OVerlap (SOV) of 66.0455. It outperforms the original BRNN and Pollastri's BRNN in both Q3 and SOV. Specifically, it improves the SOV score by 4-6%.

The effect of netting solidity ratio and inclined angle on the hydrodynamic characteristics of knotless polyethylene netting

Science.gov (United States)

Tang, Hao; Hu, Fuxiang; Xu, Liuxiong; Dong, Shuchuang; Zhou, Cheng; Wang, Xuefang

2017-10-01

Knotless polyethylene (PE) netting has been widely used in aquaculture cages and fishing gears, especially in Japan. In this study, the hydrodynamic coefficient of six knotless PE netting panels with different solidity ratios were assessed in a flume tank under various attack angles of netting from 0° (parallel to flow) to 90° (perpendicular to flow) and current speeds from 40 cm s-1 to 130 cm s-1. It was found that the drag coefficient was related to Reynolds number, solidity ratio and attack angle of netting. The solidity ratio was positively related with drag coefficient for netting panel perpendicular to flow, whereas when setting the netting panel parallel to the flow the opposite result was obtained. For netting panels placed at an angle to the flow, the lift coefficient reached the maximum at an attack angle of 50° and then decreased as the attack angle further increased. The solidity ratio had a dual influence on drag coefficient of inclined netting panels. Compared to result in the literature, the normal drag coefficient of knotless PE netting measured in this study is larger than that of nylon netting or Dyneema netting.

Use of bed nets and factors that influence bed net use among Jinuo Ethnic Minority in southern China.

Science.gov (United States)

Xu, Jian-wei; Liao, Yuan-mei; Liu, Hui; Nie, Ren-hua; Havumaki, Joshua

2014-01-01

Insecticide-treated nets (ITNs) are an integral part of vector control recommendations for malaria elimination in China. This study investigated the extent to which bed nets were used and which factors influence bed net use among Jinuo Ethnic Minority in China-Myanmar-Laos border areas. This study combined a quantitative household questionnaire survey and qualitative semi-structured in-depth interviews (SDI). Questionnaires were administered to 352 heads of households. SDIs were given to 20 key informants. The bed net to person ratio was 1∶2.1 (i.e., nearly one net for every two people), however only 169 (48.0%) households owned at least one net and 623 (47.2%) residents slept under bed nets the prior night. The percentages of residents who regularly slept under nets (RSUN) and slept under nets the prior night (SUNPN) were similar (48.0% vs. 47.2%, P>0.05), however the percentage correct use of nets (CUN) was significantly lower (34.5%, Pcash income per person (ACIP) was an independent factor that influenced bed net use (PHigh bed net availability does not necessarily mean higher coverage or bed net use. Household income, house type and knowledge of the ability of bed nets to prevent malaria are all independent factors that influence bed net use among Jinuo Ethnic Minority.

Fusion through the NET

International Nuclear Information System (INIS)

Spears, B.

1987-01-01

The paper concerns the next generation of fusion machines which are intended to demonstrate the technical viability of fusion. In Europe, the device that will follow on from JET is known as NET - the Next European Torus. If the design programme for NET proceeds, Europe could start to build the machine in 1994. The present JET programme hopes to achieve breakeven in the early 1990's. NET hopes to reach ignition in the next century, and so lay the foundation for a demonstration reactor. A description is given of the technical specifications of the components of NET, including: the first wall, the divertors to protect the wall, the array of magnets that provide the fields containing the plasma, the superconducting magnets, and the shield of the machine. NET's research programme is briefly outlined, including the testing programme to optimise conditions in the machine to achieve ignition, and its safety work. (U.K.)

NetView technical research

Science.gov (United States)

1993-01-01

This is the Final Technical Report for the NetView Technical Research task. This report is prepared in accordance with Contract Data Requirements List (CDRL) item A002. NetView assistance was provided and details are presented under the following headings: NetView Management Systems (NMS) project tasks; WBAFB IBM 3090; WPAFB AMDAHL; WPAFB IBM 3084; Hill AFB; McClellan AFB AMDAHL; McClellan AFB IBM 3090; and Warner-Robins AFB.

Efficacy of PermaNet® 3.0 and PermaNet® 2.0 nets against laboratory-reared and wild Anopheles gambiae sensu lato populations in northern Tanzania.

Science.gov (United States)

Kweka, Eliningaya J; Lyaruu, Lucile J; Mahande, Aneth M

2017-01-18

Mosquitoes have developed resistance against pyrethroids, the only class of insecticides approved for use on long-lasting insecticidal nets (LLINs). The present study sought to evaluate the efficacy of the pyrethroid synergist PermaNet® 3.0 LLIN versus the pyrethroid-only PermaNet® 2.0 LLIN, in an East African hut design in Lower Moshi, northern Tanzania. In this setting, resistance to pyrethroid insecticides has been identified in Anopheles gambiae mosquitoes. Standard World Health Organization bioefficacy evaluations were conducted in both laboratory and experimental huts. Experimental hut evaluations were conducted in an area where there was presence of a population of highly pyrethroid-resistant An. arabiensis mosquitoes. All nets used were subjected to cone bioassays and then to experimental hut trials. Mosquito mortality, blood-feeding inhibition and personal protection rate were compared between untreated nets, unwashed LLINs and LLINs that were washed 20 times. Both washed and unwashed PermaNet® 2.0 and PermaNet® 3.0 LLINs had knockdown and mortality rates of 100% against a susceptible strain of An. gambiae sensu stricto. The adjusted mortality rate of the wild mosquito population after use of the unwashed PermaNet® 3.0 and PermaNet® 2.0 nets was found to be higher than after use of the washed PermaNet® 2.0 and PermaNet® 3.0 nets. Given the increasing incidence of pyrethroid resistance in An. gambiae mosquitoes in Tanzania, we recommend that consideration is given to its distribution in areas with pyrethroid-resistant malaria vectors within the framework of a national insecticide-resistance management plan.

PODATKOVNE STORITVE ADO.NET IN ADO.NET ENTITY FRAMEWORK

OpenAIRE

Volavc, Franc

2012-01-01

V diplomskem delu smo predstavili Microsoftovi ogrodji ADO.NET in ADO.NET Entity Framework. Preučili in analizirali smo metode za dostop do podatkovnih virov, ki jih ponujata ogrodji, ter nato te ugotovitve preslikati v odločitveno drevo, katero bo programerjem in razvijalcem informacijskih sistemov pomagalo pri odločanju glede pristopa za dostop do podatkovnih virov. Ker bomo v diplomskem delu predstavili Microsoftovi ogrodji, bomo posledično omejeni zgolj na Microsoftovo tehnologijo, se pra...

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

OpenAIRE

Kang, Kai; Li, Hongsheng; Yan, Junjie; Zeng, Xingyu; Yang, Bin; Xiao, Tong; Zhang, Cong; Wang, Zhe; Wang, Ruohui; Wang, Xiaogang; Ouyang, Wanli

2016-01-01

The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and context...

Blanket testing in NET

International Nuclear Information System (INIS)

Chazalon, M.; Daenner, W.; Libin, B.

1989-01-01

The testing stages in NET for the performance assessment of the various breeding blanket concepts developed at the present time in Europe for DEMO (LiPb and ceramic blankets) and the requirements upon NET to perform these tests are reviewed. Typical locations available in NET for blanket testing are the central outboard segments and the horizontal ports of in-vessel sectors. These test positions will be connectable with external test loops. The number of test loops (helium, water, liquid metal) will be such that each major class of blankets can be tested in NET. The test positions, the boundary conditions and the external test loops are identified and the requirements for test blankets are summarized (author). 6

Neural network fusion capabilities for efficient implementation of tracking algorithms

Science.gov (United States)

Sundareshan, Malur K.; Amoozegar, Farid

1997-03-01

The ability to efficiently fuse information of different forms to facilitate intelligent decision making is one of the major capabilities of trained multilayer neural networks that is now being recognized. While development of innovative adaptive control algorithms for nonlinear dynamical plants that attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. We describe the capabilities and functionality of neural network algorithms for data fusion and implementation of tracking filters. To discuss details and to serve as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target- tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes from the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. A system architecture that efficiently integrates the fusion capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described. The innovation lies in the way the fusion of multisensor data is accomplished to facilitate improved estimation without increasing the computational complexity of the dynamical state estimator itself.

A universal multilingual weightless neural network tagger via quantitative linguistics.

Science.gov (United States)

Carneiro, Hugo C C; Pedreira, Carlos E; França, Felipe M G; Lima, Priscila M V

2017-07-01

In the last decade, given the availability of corpora in several distinct languages, research on multilingual part-of-speech tagging started to grow. Amongst the novelties there is mWANN-Tagger (multilingual weightless artificial neural network tagger), a weightless neural part-of-speech tagger capable of being used for mostly-suffix-oriented languages. The tagger was subjected to corpora in eight languages of quite distinct natures and had a remarkable accuracy with very low sample deviation in every one of them, indicating the robustness of weightless neural systems for part-of-speech tagging tasks. However, mWANN-Tagger needed to be tuned for every new corpus, since each one required a different parameter configuration. For mWANN-Tagger to be truly multilingual, it should be usable for any new language with no need of parameter tuning. This article proposes a study that aims to find a relation between the lexical diversity of a language and the parameter configuration that would produce the best performing mWANN-Tagger instance. Preliminary analyses suggested that a single parameter configuration may be applied to the eight aforementioned languages. The mWANN-Tagger instance produced by this configuration was as accurate as the language-dependent ones obtained through tuning. Afterwards, the weightless neural tagger was further subjected to new corpora in languages that range from very isolating to polysynthetic ones. The best performing instances of mWANN-Tagger are again the ones produced by the universal parameter configuration. Hence, mWANN-Tagger can be applied to new corpora with no need of parameter tuning, making it a universal multilingual part-of-speech tagger. Further experiments with Universal Dependencies treebanks reveal that mWANN-Tagger may be extended and that it has potential to outperform most state-of-the-art part-of-speech taggers if better word representations are provided. Copyright © 2017 Elsevier Ltd. All rights reserved.

Alteration of neural action potential patterns by axonal stimulation: the importance of stimulus location.

Science.gov (United States)

Crago, Patrick E; Makowski, Nathaniel S

2014-10-01

Stimulation of peripheral nerves is often superimposed on ongoing motor and sensory activity in the same axons, without a quantitative model of the net action potential train at the axon endpoint. We develop a model of action potential patterns elicited by superimposing constant frequency axonal stimulation on the action potentials arriving from a physiologically activated neural source. The model includes interactions due to collision block, resetting of the neural impulse generator, and the refractory period of the axon at the point of stimulation. Both the mean endpoint firing rate and the probability distribution of the action potential firing periods depend strongly on the relative firing rates of the two sources and the intersite conduction time between them. When the stimulus rate exceeds the neural rate, neural action potentials do not reach the endpoint and the rate of endpoint action potentials is the same as the stimulus rate, regardless of the intersite conduction time. However, when the stimulus rate is less than the neural rate, and the intersite conduction time is short, the two rates partially sum. Increases in stimulus rate produce non-monotonic increases in endpoint rate and continuously increasing block of neurally generated action potentials. Rate summation is reduced and more neural action potentials are blocked as the intersite conduction time increases. At long intersite conduction times, the endpoint rate simplifies to being the maximum of either the neural or the stimulus rate. This study highlights the potential of increasing the endpoint action potential rate and preserving neural information transmission by low rate stimulation with short intersite conduction times. Intersite conduction times can be decreased with proximal stimulation sites for muscles and distal stimulation sites for sensory endings. The model provides a basis for optimizing experiments and designing neuroprosthetic interventions involving motor or sensory stimulation.

Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

Science.gov (United States)

Mioulet, L.; Bideault, G.; Chatelain, C.; Paquet, T.; Brunessaux, S.

2015-01-01

The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

The Use of Neural Network to Recognize the Parts of the Computer Motherboard

OpenAIRE

Abbas M. Ali; S. D. Gore; Musaab AL-Sarierah

2005-01-01

This study suggests a new approach of learning which utilizes the techniques of computer vision to recognize the parts inside the motherboard. The main thrust is to identify different parts of the motherboard using a Hopfield Neural Network. The outcome of the net is compared with the objects stored in the database. The proposed scheme is implemented using bottom -up approach, where steps like edge detection, spatial filtering, image masking..etc are performed in sequence. the scheme is simul...

Current Status and Future Prospect of K-NET and KiK-net

Science.gov (United States)

Aoi, S.; Kunugi, T.; Suzuki, W.; Nakamura, H.; Fujiwara, H.

2014-12-01

During 18 years since the deployment of K-NET following the Kobe earthquake, our attention has mainly focused on rapidity of the data collection and an unfailing and reliable observation. In this presentation, we review three generations of the instruments employed by K-NET and KiK-net from these two points of view.At beginning of the 2000's, we newly developed the second generation instruments (K-NET02, K-NET02A, KiK-net06) to replace the first generation instruments (K-NET95, SMAC-MDK) employed when the networks were constructed in the 1990's. These instruments have an automatic dial-out function. It takes typically 2-5 s to establish communication and a few seconds to send the pre-trigger data. After that, data is available typically within a 1.5 s delay. Not only waveform data but also strong motion indexes such as real-time intensity, PGA, PGV, PGD, and response spectra are continuously sent once a second.After the 2011 Tohoku earthquake, we have developed the third generation instruments (K-NET11, KiK-net11) and have replaced almost half of the all stations country wide. Main improvement of this instrument is more unfailing and reliable observation. Because we have often experienced very large ground motions (e.g. 45 records exceeding gravity), the maximum measureable range was expanded from 2000 gal to 4000 gal for the second generation instrument, and to 8000 gal for the third. For the third generation instrument, in case of power failure, observation (including transmission of data) works for seven days thanks to the backup battery, while for the second generation instruments it works only for one day. By adding an oblique component to the three-component accelerometers, we could automatically distinguish shaking data from noise such as electric pulses which may cause a false alarm in EEW. Implementation to guarantee the continuity of observation under severe conditions such as during the Tohoku earthquake is very important, as well as a highly efficient

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

Science.gov (United States)

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

Comparison of logistic regression and neural models in predicting the outcome of biopsy in breast cancer from MRI findings

International Nuclear Information System (INIS)

Abdolmaleki, P.; Yarmohammadi, M.; Gity, M.

2004-01-01

Background: We designed an algorithmic model based on regression analysis and a non-algorithmic model based on the Artificial Neural Network. Materials and methods: The ability of these models was compared together in clinical application to differentiate malignant from benign breast tumors in a study group of 161 patient's records. Each patient's record consisted of 6 subjective features extracted from MRI appearance. These findings were enclosed as features extracted for an Artificial Neural Network as well as a logistic regression model to predict biopsy outcome. After both models had been trained perfectly on samples (n=100), the validation samples (n=61) were presented to the trained network as well as the established logistic regression models. Finally, the diagnostic performance of models were compared to the that of the radiologist in terms of sensitivity, specificity and accuracy, using receiver operating characteristic curve analysis. Results: The average out put of the Artificial Neural Network yielded a perfect sensitivity (98%) and high accuracy (90%) similar to that one of an expert radiologist (96% and 92%) while specificity was smaller than that (67%) verses 80%). The output of the logistic regression model using significant features showed improvement in specificity from 60% for the logistic regression model using all features to 93% for the reduced logistic regression model, keeping the accuracy around 90%. Conclusion: Results show that Artificial Neural Network and logistic regression model prove the relationship between extracted morphological features and biopsy results. Using statistically significant variables reduced logistic regression model outperformed of Artificial Neural Network with remarkable specificity while keeping high sensitivity is achieved

Multispectral confocal microscopy images and artificial neural nets to monitor the photosensitizer uptake and degradation in Candida albicans cells

Science.gov (United States)

Romano, Renan A.; Pratavieira, Sebastião.; da Silva, Ana P.; Kurachi, Cristina; Guimarães, Francisco E. G.

2017-07-01

This study clearly demonstrates that multispectral confocal microscopy images analyzed by artificial neural networks provides a powerful tool to real-time monitoring photosensitizer uptake, as well as photochemical transformations occurred.

An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

Science.gov (United States)

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Markets, voucher subsidies and free nets combine to achieve high bed net coverage in rural Tanzania

Directory of Open Access Journals (Sweden)

Gerrets Rene PM

2008-06-01

Full Text Available Abstract Background Tanzania has a well-developed network of commercial ITN retailers. In 2004, the government introduced a voucher subsidy for pregnant women and, in mid 2005, helped distribute free nets to under-fives in small number of districts, including Rufiji on the southern coast, during a child health campaign. Contributions of these multiple insecticide-treated net delivery strategies existing at the same time and place to coverage in a poor rural community were assessed. Methods Cross-sectional household survey in 6,331 members of randomly selected 1,752 households of 31 rural villages of Demographic Surveillance System in Rufiji district, Southern Tanzania was conducted in 2006. A questionnaire was administered to every consenting respondent about net use, treatment status and delivery mechanism. Findings Net use was 62.7% overall, 87.2% amongst infants (0 to1 year, 81.8% amongst young children (>1 to 5 years, 54.5% amongst older children (6 to 15 years and 59.6% amongst adults (>15 years. 30.2% of all nets had been treated six months prior to interview. The biggest source of nets used by infants was purchase from the private sector with a voucher subsidy (41.8%. Half of nets used by young children (50.0% and over a third of those used by older children (37.2% were obtained free of charge through the vaccination campaign. The largest source of nets amongst the population overall was commercial purchase (45.1% use and was the primary means for protecting adults (60.2% use. All delivery mechanisms, especially sale of nets at full market price, under-served the poorest but no difference in equity was observed between voucher-subsidized and freely distributed nets. Conclusion All three delivery strategies enabled a poor rural community to achieve net coverage high enough to yield both personal and community level protection for the entire population. Each of them reached their relevant target group and free nets only temporarily

Initial CAD investigations for NET

International Nuclear Information System (INIS)

Katz, F.; Leinemann, K.; Ludwig, A.; Marek, U.; Olbrich, W.; Schlechtendahl, E.G.

1985-11-01

This report summarizes the work done under contract no. 164/84-7/FU-D-/NET between the Commission of the European Communities and KfK during the period from June 1, 1984, through May 31, 1985. The following topics are covered in this report: Initial modelling of NET version NET2A, CAD system extension for remote handling studies, analysis of the CAD information structure, work related to the transfer of CAD information between KfK and the NET team. (orig.) [de

Convolutional neural network architectures for predicting DNA–protein binding

Science.gov (United States)

Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

2016-01-01

Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

NetBeans IDE 8 cookbook

CERN Document Server

Salter, David

2014-01-01

If you're a Java developer of any level using NetBeans and want to learn how to get the most out of NetBeans, then this book is for you. Learning how to utilize NetBeans will provide a firm foundation for your Java application development.

The Net Advance of Physics

Science.gov (United States)

THE NET ADVANCE OF PHYSICS Review Articles and Tutorials in an Encyclopædic Format Established 1995 [Link to MIT] Computer support for The Net Advance of Physics is furnished by The Massachusetts Newest Additions SPECIAL FEATURES: Net Advance RETRO: Nineteenth Century Physics History of Science

Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images.

Science.gov (United States)

Huang, Yue; Zheng, Han; Liu, Chi; Ding, Xinghao; Rohde, Gustavo K

2017-11-01

Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our paper assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.

Improved netting

International Nuclear Information System (INIS)

Bramley, A.; Clabburn, R.J.T.

1976-01-01

A method is described for producing netting composed of longitudinal and transverse threads of irradiation cross linked thermoplastic material, the threads being joined together at their crossings by moulded masses of cross linked thermoplastic material. The thread may be formed of polyethylene filaments, subjected to a radiation dose of 15 to 25 MR. The moulding can be conducted at 245 0 to 260 0 C or higher. The product is claimed to be an improved quality of netting, with bonds of increased strength between crossing threads. (U.K.)

A neural network detection system for lower-hybrid cavities in electron plasma density measured by the FREJA satellite

International Nuclear Information System (INIS)

Waldemark, J.; Karlsson, Jan

1995-03-01

This paper presents a lower-hybrid cavity detection system, CDS, for measurements of electron plasma density on the FREJA satellite wave experiment. The system can reduce the amount of data to be analysed by as much as 96% and still retain more than 85% of the desired information. The CDS is a combination of a hybrid neural network, HNN and expert rules. The HNN is a Self Organizing Map, SOM, combined with a feed forward back propagation neural net, BP. The CDS can be controlled by the user to operate with various degrees of sensitivity. Maximum detection capability is as high as 95% with data reduction lowered to 85%. 10 refs

Net alkalinity and net acidity 1: Theoretical considerations

International Nuclear Information System (INIS)

Kirby, Carl S.; Cravotta, Charles A.

2005-01-01

Net acidity and net alkalinity are widely used, poorly defined, and commonly misunderstood parameters for the characterization of mine drainage. The authors explain theoretical expressions of 3 types of alkalinity (caustic, phenolphthalein, and total) and acidity (mineral, CO 2 , and total). Except for rarely-invoked negative alkalinity, theoretically defined total alkalinity is closely analogous to measured alkalinity and presents few practical interpretation problems. Theoretically defined 'CO 2 -acidity' is closely related to most standard titration methods with an endpoint pH of 8.3 used for determining acidity in mine drainage, but it is unfortunately named because CO 2 is intentionally driven off during titration of mine-drainage samples. Using the proton condition/mass-action approach and employing graphs to illustrate speciation with changes in pH, the authors explore the concept of principal components and how to assign acidity contributions to aqueous species commonly present in mine drainage. Acidity is defined in mine drainage based on aqueous speciation at the sample pH and on the capacity of these species to undergo hydrolysis to pH 8.3. Application of this definition shows that the computed acidity in mgL -1 as CaCO 3 (based on pH and analytical concentrations of dissolved Fe II , Fe III , Mn, and Al in mgL -1 ):acidity calculated =50{1000(10 -pH )+[2(Fe II )+3(Fe III )]/56+2(Mn) /55+3(Al)/27}underestimates contributions from HSO 4 - and H + , but overestimates the acidity due to Fe 3+ and Al 3+ . However, these errors tend to approximately cancel each other. It is demonstrated that 'net alkalinity' is a valid mathematical construction based on theoretical definitions of alkalinity and acidity. Further, it is shown that, for most mine-drainage solutions, a useful net alkalinity value can be derived from: (1) alkalinity and acidity values based on aqueous speciation (2) measured alkalinity minus calculated acidity, or (3) taking the negative of the

Net alkalinity and net acidity 1: Theoretical considerations

Science.gov (United States)

Kirby, C.S.; Cravotta, C.A.

2005-01-01

Net acidity and net alkalinity are widely used, poorly defined, and commonly misunderstood parameters for the characterization of mine drainage. The authors explain theoretical expressions of 3 types of alkalinity (caustic, phenolphthalein, and total) and acidity (mineral, CO2, and total). Except for rarely-invoked negative alkalinity, theoretically defined total alkalinity is closely analogous to measured alkalinity and presents few practical interpretation problems. Theoretically defined "CO 2-acidity" is closely related to most standard titration methods with an endpoint pH of 8.3 used for determining acidity in mine drainage, but it is unfortunately named because CO2 is intentionally driven off during titration of mine-drainage samples. Using the proton condition/mass- action approach and employing graphs to illustrate speciation with changes in pH, the authors explore the concept of principal components and how to assign acidity contributions to aqueous species commonly present in mine drainage. Acidity is defined in mine drainage based on aqueous speciation at the sample pH and on the capacity of these species to undergo hydrolysis to pH 8.3. Application of this definition shows that the computed acidity in mg L -1 as CaCO3 (based on pH and analytical concentrations of dissolved FeII, FeIII, Mn, and Al in mg L -1):aciditycalculated=50{1000(10-pH)+[2(FeII)+3(FeIII)]/56+2(Mn)/ 55+3(Al)/27}underestimates contributions from HSO4- and H+, but overestimates the acidity due to Fe3+ and Al3+. However, these errors tend to approximately cancel each other. It is demonstrated that "net alkalinity" is a valid mathematical construction based on theoretical definitions of alkalinity and acidity. Further, it is shown that, for most mine-drainage solutions, a useful net alkalinity value can be derived from: (1) alkalinity and acidity values based on aqueous speciation, (2) measured alkalinity minus calculated acidity, or (3) taking the negative of the value obtained in a

Proof Nets for Lambek Calculus

NARCIS (Netherlands)

Roorda, Dirk

1992-01-01

The proof nets of linear logic are adapted to the non-commutative Lambek calculus. A different criterion for soundness of proof nets is given, which gives rise to new algorithms for proof search. The order sensitiveness of the Lambek calculus is reflected by the planarity condition on proof nets;

Properties of porous netted materials

International Nuclear Information System (INIS)

Daragan, V.D.; Drozdov, B.G.; Kotov, A.Yu.; Mel'nikov, G.N.; Pustogarov, A.V.

1987-01-01

Hydraulic and strength characteristics, efficient heat conduction and inner heat exchange coefficient are experimentally studied for porous netted materials on the base of the brass nets as dependent on porosity, cell size and method of net laying. Results of the studies are presented. It is shown that due to anisotropy of the material properties the hydraulic resistance in the direction parallel to the nets plane is 1.3-1.6 times higher than in the perpendicular one. Values of the effective heat conduction in the direction perpendicular to the nets plane at Π>0.45 agree with the data from literature, at Π<0.45 a deviation from the calculated values is marked in the direction of the heat conduction decrease

Learning of N-layers neural network

Directory of Open Access Journals (Sweden)

Vladimír Konečný

2005-01-01

Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.

Understanding Net Zero Energy Buildings

DEFF Research Database (Denmark)

Salom, Jaume; Widén, Joakim; Candanedo, José

2011-01-01

Although several alternative definitions exist, a Net-Zero Energy Building (Net ZEB) can be succinctly described as a grid-connected building that generates as much energy as it uses over a year. The “net-zero” balance is attained by applying energy conservation and efficiency measures...... and by incorporating renewable energy systems. While based on annual balances, a complete description of a Net ZEB requires examining the system at smaller time-scales. This assessment should address: (a) the relationship between power generation and building loads and (b) the resulting interaction with the power grid...

Hopfield neural network and optical fiber sensor as intelligent heart rate monitor

Science.gov (United States)

Mutter, Kussay Nugamesh

2018-01-01

This paper presents a design and fabrication of an intelligent fiber-optic sensor used for examining and monitoring heart rate activity. It is found in the literature that the use of fiber sensors as heart rate sensor is widely studied. However, the use of smart sensors based on Hopfield neural networks is very low. In this work, the sensor is a three fibers without cladding of about 1 cm, fed by laser light of 1550 nm of wavelength. The sensing portions are mounted with a micro sensitive diaphragm to transfer the pulse pressure on the left radial wrist. The influenced light intensity will be detected by a three photodetectors as inputs into the Hopfield neural network algorithm. The latter is a singlelayer auto-associative memory structure with a same input and output layers. The prior training weights are stored in the net memory for the standard recorded normal heart rate signals. The sensors' heads work on the reflection intensity basis. The novelty here is that the sensor uses a pulse pressure and Hopfield neural network in an integrity approach. The results showed a significant output measurements of heart rate and counting with a plausible error rate.

History-dependent stochastic Petri nets

NARCIS (Netherlands)

Schonenberg, H.; Sidorova, N.; Aalst, van der W.M.P.; Hee, van K.M.; Pnueli, A.; Virbitskaite, I.; Voronkov, A.

2010-01-01

Stochastic Petri Nets are a useful and well-known tool for performance analysis. However, an implicit assumption in the different types of Stochastic Petri Nets is the Markov property. It is assumed that a choice in the Petri net only depends on the current state and not on earlier choices. For many

Topology and computational performance of attractor neural networks

International Nuclear Information System (INIS)

McGraw, Patrick N.; Menzinger, Michael

2003-01-01

To explore the relation between network structure and function, we studied the computational performance of Hopfield-type attractor neural nets with regular lattice, random, small-world, and scale-free topologies. The random configuration is the most efficient for storage and retrieval of patterns by the network as a whole. However, in the scale-free case retrieval errors are not distributed uniformly among the nodes. The portion of a pattern encoded by the subset of highly connected nodes is more robust and efficiently recognized than the rest of the pattern. The scale-free network thus achieves a very strong partial recognition. The implications of these findings for brain function and social dynamics are suggestive

Pro ASP.NET 4 in VB 2010

CERN Document Server

MacDonald, Matthew; Freeman, Adam; Szpuszta, Mario; Agarwal, Vidya Vrat

2010-01-01

ASP.NET 4 is the latest version of Microsoft's revolutionary ASP.NET technology. It is the principal standard for creating dynamic web pages on the Windows platform. Pro ASP.NET 4 in VB 2010 raises the bar for high-quality, practical advice on learning and deploying Microsoft's dynamic web solution. This new edition is updated with everything you need to come to grips with the latest version of ASP.NET, including coverage of ASP.NET MVC, ASP.NET AJAX 4, ASP.NET Dynamic Data, and Silverlight 3. Seasoned .NET professionals Matthew MacDonald and Mario Szpuszta explain how you can get the most fro

Neural network modelling of planform geometry of headland-bay beaches

Science.gov (United States)

Iglesias, G.; López, I.; Castro, A.; Carballo, R.

2009-02-01

The shoreline of beaches in the lee of coastal salients or man-made structures, usually known as headland-bay beaches, has a distinctive curvature; wave fronts curve as a result of wave diffraction at the headland and in turn cause the shoreline to bend. The ensuing curved planform is of great interest both as a peculiar landform and in the context of engineering projects in which it is necessary to predict how a coastal structure will affect the sandy shoreline in its lee. A number of empirical models have been put forward, each based on a specific equation. A novel approach, based on the application of artificial neural networks, is presented in this work. Unlike the conventional method, no particular equation of the planform is embedded in the model. Instead, it is the model itself that learns about the problem from a series of examples of headland-bay beaches (the training set) and thereafter applies this self-acquired knowledge to other cases (the test set) for validation. Twenty-three headland-bay beaches from around the world were selected, of which sixteen and seven make up the training and test sets, respectively. As there is no well-developed theory for deciding upon the most convenient neural network architecture to deal with a particular data set, an experimental study was conducted in which ten different architectures with one and two hidden neuron layers and five training algorithms - 50 different options combining network architecture and training algorithm - were compared. Each of these options was implemented, trained and tested in order to find the best-performing approach for modelling the planform of headland-bay beaches. Finally, the selected neural network model was compared with a state-of-the-art planform model and was shown to outperform it.

Modelling innovation performance of European regions using multi-output neural networks.

Science.gov (United States)

Hajek, Petr; Henriques, Roberto

2017-01-01

Regional innovation performance is an important indicator for decision-making regarding the implementation of policies intended to support innovation. However, patterns in regional innovation structures are becoming increasingly diverse, complex and nonlinear. To address these issues, this study aims to develop a model based on a multi-output neural network. Both intra- and inter-regional determinants of innovation performance are empirically investigated using data from the 4th and 5th Community Innovation Surveys of NUTS 2 (Nomenclature of Territorial Units for Statistics) regions. The results suggest that specific innovation strategies must be developed based on the current state of input attributes in the region. Thus, it is possible to develop appropriate strategies and targeted interventions to improve regional innovation performance. We demonstrate that support of entrepreneurship is an effective instrument of innovation policy. We also provide empirical support that both business and government R&D activity have a sigmoidal effect, implying that the most effective R&D support should be directed to regions with below-average and average R&D activity. We further show that the multi-output neural network outperforms traditional statistical and machine learning regression models. In general, therefore, it seems that the proposed model can effectively reflect both the multiple-output nature of innovation performance and the interdependency of the output attributes.

Modelling innovation performance of European regions using multi-output neural networks.

Directory of Open Access Journals (Sweden)

Petr Hajek

Full Text Available Regional innovation performance is an important indicator for decision-making regarding the implementation of policies intended to support innovation. However, patterns in regional innovation structures are becoming increasingly diverse, complex and nonlinear. To address these issues, this study aims to develop a model based on a multi-output neural network. Both intra- and inter-regional determinants of innovation performance are empirically investigated using data from the 4th and 5th Community Innovation Surveys of NUTS 2 (Nomenclature of Territorial Units for Statistics regions. The results suggest that specific innovation strategies must be developed based on the current state of input attributes in the region. Thus, it is possible to develop appropriate strategies and targeted interventions to improve regional innovation performance. We demonstrate that support of entrepreneurship is an effective instrument of innovation policy. We also provide empirical support that both business and government R&D activity have a sigmoidal effect, implying that the most effective R&D support should be directed to regions with below-average and average R&D activity. We further show that the multi-output neural network outperforms traditional statistical and machine learning regression models. In general, therefore, it seems that the proposed model can effectively reflect both the multiple-output nature of innovation performance and the interdependency of the output attributes.

Prediction of municipal water production in touristic Mecca City in Saudi Arabia using neural networks

Directory of Open Access Journals (Sweden)

AbdelHamid Ajbar

2015-01-01

Full Text Available Accurate forecast of municipal water production is critically important for arid and oil rich countries such as Saudi Arabia which depend on costly desalination plants to satisfy the growing water demand. Achieving the desired prediction accuracy is a challenging task since the forecast model should take into consideration a variety of factors such as economic development, climate conditions and population growth. The task is further complicated given that Mecca city is visited regularly by large numbers during specific months in the year due to religious reasons. This study develops a neural network model for forecasting the monthly and annual water demand for Mecca city, Saudi Arabia. The proposed model used historic records of water production and estimated visitors’ distribution to calibrate a neural network model for water demand forecast. The explanatory variables included annually-varying variables such as household income, persons per household, and city population, along with monthly-varying variables such as expected number of visitors each month and maximum monthly temperature. The NN prediction outperforms that of a regular econometric model. The latter is adjusted such that it can provide monthly and annual predictions.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

Science.gov (United States)

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Axial design of fuel for BWRs using neural networks; Diseno axial de combustible para BWRs usando redes neuronales

Energy Technology Data Exchange (ETDEWEB)

Ortiz, J.J.; Castillo, A.; Montes, J.L.; Perusquia, R. [ININ, Carretera Mexico-Toluca s/n, 52750 La Marquesa, Ocoyoacac, Estado de Mexico (Mexico)]. e-mail: jjortiz@nuclear.inin.mx

2007-07-01

In this work a new system of axial optimization of fuel is presented based on a recurrent multi state neural net called RENODC. They are described with detail the main characteristics of this type of neural net (architecture, energy function and actualization of neural states) and like was adapted to the assemble design of nuclear fuel. The fuel design is proven by means of a fuel recharge and pre determined control rod patterns. By this way a good axial fuel design one has, when the thermal limits are fulfilled along the cycle, the reactor stays critic and at least the wanted longitude of the cycle is reached; also the margin of in cold turned off is verified. The assemble of fuel created with RENODC it is substituted by a recharge assemble and it is sought to verify that the energy requirements and aspects of safety are completed. The used cycle corresponds to a balance cycle of 18 months that it can be applied to the Laguna Verde Nucleo electric Central. The tests demonstrate the effectiveness of the system to reach satisfactory results in times of CPU of around 4 hours. This way, it could be proven that the design proposed with a lightly superior enrichment to that of the substituted design, fulfills the energy requirements. In later stages of this project this system will be coupled to the other optimization modules that are already had. (Author)

NASA Net Zero Energy Buildings Roadmap

Energy Technology Data Exchange (ETDEWEB)

Pless, S.; Scheib, J.; Torcellini, P.; Hendron, B.; Slovensky, M.

2014-10-01

In preparation for the time-phased net zero energy requirement for new federal buildings starting in 2020, set forth in Executive Order 13514, NASA requested that the National Renewable Energy Laboratory (NREL) to develop a roadmap for NASA's compliance. NASA detailed a Statement of Work that requested information on strategic, organizational, and tactical aspects of net zero energy buildings. In response, this document presents a high-level approach to net zero energy planning, design, construction, and operations, based on NREL's first-hand experience procuring net zero energy construction, and based on NREL and other industry research on net zero energy feasibility. The strategic approach to net zero energy starts with an interpretation of the executive order language relating to net zero energy. Specifically, this roadmap defines a net zero energy acquisition process as one that sets an aggressive energy use intensity goal for the building in project planning, meets the reduced demand goal through energy efficiency strategies and technologies, then adds renewable energy in a prioritized manner, using building-associated, emission- free sources first, to offset the annual energy use required at the building; the net zero energy process extends through the life of the building, requiring a balance of energy use and production in each calendar year.

RESTful NET

CERN Document Server

Flanders, Jon

2008-01-01

RESTful .NET is the first book that teaches Windows developers to build RESTful web services using the latest Microsoft tools. Written by Windows Communication Foundation (WFC) expert Jon Flanders, this hands-on tutorial demonstrates how you can use WCF and other components of the .NET 3.5 Framework to build, deploy and use REST-based web services in a variety of application scenarios. RESTful architecture offers a simpler approach to building web services than SOAP, SOA, and the cumbersome WS- stack. And WCF has proven to be a flexible technology for building distributed systems not necessa

Getting to Net Zero

Energy Technology Data Exchange (ETDEWEB)

2016-09-01

The technology necessary to build net zero energy buildings (NZEBs) is ready and available today, however, building to net zero energy performance levels can be challenging. Energy efficiency measures, onsite energy generation resources, load matching and grid interaction, climatic factors, and local policies vary from location to location and require unique methods of constructing NZEBs. It is recommended that Components start looking into how to construct and operate NZEBs now as there is a learning curve to net zero construction and FY 2020 is just around the corner.

Net Zero Energy Buildings

DEFF Research Database (Denmark)

Marszal, Anna Joanna; Bourrelle, Julien S.; Gustavsen, Arild

2010-01-01

and identify possible renewable energy supply options which may be considered in calculations. Finally, the gap between the methodology proposed by each organisation and their respective national building code is assessed; providing an overview of the possible changes building codes will need to undergo......The international cooperation project IEA SHC Task 40 / ECBCS Annex 52 “Towards Net Zero Energy Solar Buildings”, attempts to develop a common understanding and to set up the basis for an international definition framework of Net Zero Energy Buildings (Net ZEBs). The understanding of such buildings...

Pro NET Best Practices

CERN Document Server

Ritchie, Stephen D

2011-01-01

Pro .NET Best Practices is a practical reference to the best practices that you can apply to your .NET projects today. You will learn standards, techniques, and conventions that are sharply focused, realistic and helpful for achieving results, steering clear of unproven, idealistic, and impractical recommendations. Pro .NET Best Practices covers a broad range of practices and principles that development experts agree are the right ways to develop software, which includes continuous integration, automated testing, automated deployment, and code analysis. Whether the solution is from a free and

ASP.NET web API build RESTful web applications and services on the .NET framework

CERN Document Server

Kanjilal, Joydip

2013-01-01

This book is a step-by-step, practical tutorial with a simple approach to help you build RESTful web applications and services on the .NET framework quickly and efficiently.This book is for ASP.NET web developers who want to explore REST-based services with C# 5. This book contains many real-world code examples with explanations whenever necessary. Some experience with C# and ASP.NET 4 is expected.

Automatic disease diagnosis using optimised weightless neural networks for low-power wearable devices.

Science.gov (United States)

Cheruku, Ramalingaswamy; Edla, Damodar Reddy; Kuppili, Venkatanareshbabu; Dharavath, Ramesh; Beechu, Nareshkumar Reddy

2017-08-01

Low-power wearable devices for disease diagnosis are used at anytime and anywhere. These are non-invasive and pain-free for the better quality of life. However, these devices are resource constrained in terms of memory and processing capability. Memory constraint allows these devices to store a limited number of patterns and processing constraint provides delayed response. It is a challenging task to design a robust classification system under above constraints with high accuracy. In this Letter, to resolve this problem, a novel architecture for weightless neural networks (WNNs) has been proposed. It uses variable sized random access memories to optimise the memory usage and a modified binary TRIE data structure for reducing the test time. In addition, a bio-inspired-based genetic algorithm has been employed to improve the accuracy. The proposed architecture is experimented on various disease datasets using its software and hardware realisations. The experimental results prove that the proposed architecture achieves better performance in terms of accuracy, memory saving and test time as compared to standard WNNs. It also outperforms in terms of accuracy as compared to conventional neural network-based classifiers. The proposed architecture is a powerful part of most of the low-power wearable devices for the solution of memory, accuracy and time issues.

Multi-National Banknote Classification Based on Visible-light Line Sensor and Convolutional Neural Network.

Science.gov (United States)

Pham, Tuyen Danh; Lee, Dong Eun; Park, Kang Ryoung

2017-07-08

Automatic recognition of banknotes is applied in payment facilities, such as automated teller machines (ATMs) and banknote counters. Besides the popular approaches that focus on studying the methods applied to various individual types of currencies, there have been studies conducted on simultaneous classification of banknotes from multiple countries. However, their methods were conducted with limited numbers of banknote images, national currencies, and denominations. To address this issue, we propose a multi-national banknote classification method based on visible-light banknote images captured by a one-dimensional line sensor and classified by a convolutional neural network (CNN) considering the size information of each denomination. Experiments conducted on the combined banknote image database of six countries with 62 denominations gave a classification accuracy of 100%, and results show that our proposed algorithm outperforms previous methods.

GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework.

Science.gov (United States)

Deng, Lei; Jiao, Peng; Pei, Jing; Wu, Zhenzhi; Li, Guoqi

2018-04-01

Although deep neural networks (DNNs) are being a revolutionary power to open up the AI era, the notoriously huge hardware overhead has challenged their applications. Recently, several binary and ternary networks, in which the costly multiply-accumulate operations can be replaced by accumulations or even binary logic operations, make the on-chip training of DNNs quite promising. Therefore there is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discrete. The second one is how to remove the full-precision hidden weights in the training phase to break the bottlenecks of memory/computation consumption. To address the first issue, we present a multi-step neuronal activation discretization method and a derivative approximation technique that enable the implementing the back propagation algorithm on discrete DNNs. While for the second issue, we propose a discrete state transition (DST) methodology to constrain the weights in a discrete space without saving the hidden weights. Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github.com/AcrossV/Gated-XNOR. More particularly, we find that when both the weights and activations become ternary values, the DNNs can be reduced to sparse binary networks, termed as gated XNOR networks (GXNOR-Nets) since only the event of non-zero weight and non-zero activation enables the control gate to start the XNOR logic operations in the original binary networks. This promises the event-driven hardware design for efficient mobile intelligence. We achieve advanced performance compared with state-of-the-art algorithms. Furthermore, the computational sparsity

Translating Colored Control Flow Nets into Readable Java via Annotated Java Workflow Nets

DEFF Research Database (Denmark)

Lassen, Kristian Bisgaard; Tjell, Simon

2007-01-01

In this paper, we present a method for developing Java applications from Colored Control Flow Nets (CCFNs), which is a special kind of Colored Petri Nets (CPNs) that we introduce. CCFN makes an explicit distinction between the representation of: The system, the environment of the system, and the ......In this paper, we present a method for developing Java applications from Colored Control Flow Nets (CCFNs), which is a special kind of Colored Petri Nets (CPNs) that we introduce. CCFN makes an explicit distinction between the representation of: The system, the environment of the system......, and the interface between the system and the environment. Our translation maps CCFNs into Anno- tated Java Workflow Nets (AJWNs) as an intermediate step, and these AJWNs are finally mapped to Java. CCFN is intended to enforce the modeler to describe the system in an imperative manner which makes the subsequent...... translation to Java easier to define. The translation to Java preserves data dependencies and control-flow aspects of the source CCFN. This paper contributes to the model-driven software development paradigm, by showing how to model a system, environment, and their interface, as a CCFN and presenting a fully...

Improvement in separation of isolated muons and pions at low pT in ATLAS hadron calorimeter using artificial neural networks technique

International Nuclear Information System (INIS)

Astvatsaturov, A.; Budagov, Yu.; Chirikov-Zorin, I.; Shigaev, V.; Paplevka, A.; Sushkov, S.; Bosman, M.; Nessi, M.

1995-01-01

Advantages of artificial neural networks techniques in handling data from highly granulated ATLAS hadron calorimeter (HC) are shown in application to isolated π/μ separation task in the range 3 T T muons have a significant probability to be absorbed in the calorimeter and therefore they cannot be reliably registered by the muon detector. The comparative analysis of main characteristics is presented for several neural net discriminators and a linear threshold discriminator operating on energy deposition in the last depth of HC. The analysis is based on MC data obtained with ATLAS simulation programs. 9 refs., 12 figs

Deep Flare Net (DeFN) Model for Solar Flare Prediction

Science.gov (United States)

Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Ishii, M.

2018-05-01

We developed a solar flare prediction model using a deep neural network (DNN) named Deep Flare Net (DeFN). This model can calculate the probability of flares occurring in the following 24 hr in each active region, which is used to determine the most likely maximum classes of flares via a binary classification (e.g., ≥M class versus statistically predict flares, the DeFN model was trained to optimize the skill score, i.e., the true skill statistic (TSS). As a result, we succeeded in predicting flares with TSS = 0.80 for ≥M-class flares and TSS = 0.63 for ≥C-class flares. Note that in usual DNN models, the prediction process is a black box. However, in the DeFN model, the features are manually selected, and it is possible to analyze which features are effective for prediction after evaluation.

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

Science.gov (United States)

Takiyama, Ken

2017-12-01

How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.

Programming NET 35

CERN Document Server

Liberty, Jesse

2009-01-01

Bestselling author Jesse Liberty and industry expert Alex Horovitz uncover the common threads that unite the .NET 3.5 technologies, so you can benefit from the best practices and architectural patterns baked into the new Microsoft frameworks. The book offers a Grand Tour" of .NET 3.5 that describes how the principal technologies can be used together, with Ajax, to build modern n-tier and service-oriented applications. "

Can Dictionary-based Computational Models Outperform the Best Linear Ones?

Czech Academy of Sciences Publication Activity Database

Gnecco, G.; Kůrková, Věra; Sanguineti, M.

2011-01-01

Roč. 24, č. 8 (2011), s. 881-887 ISSN 0893-6080 R&D Project s: GA MŠk OC10047 Grant - others:CNR - AV ČR project 2010-2012(XE) Complexity of Neural-Network and Kernel Computational Models Institutional research plan: CEZ:AV0Z10300504 Keywords : dictionary-based approximation * linear approximation * rates of approximation * worst-case error * Kolmogorov width * perceptron networks Subject RIV: IN - Informatics, Computer Science Impact factor: 2.182, year: 2011

Net metering: zero electricity bill

International Nuclear Information System (INIS)

Mangi, A.; Khan, Z.

2011-01-01

Worldwide move towards renewable energy sources, environmental concerns and decentralization of the power sector have made net metering an attractive option for power generation at small scale. This paper discusses the net metering, economical issues of renewable sources in Pakistan, technical aspects, installation suitability according to varying terrain, existing utility rules and formulation of legislation for net metering making it economically attractive. (author)

NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8-11.

Science.gov (United States)

Lundegaard, Claus; Lamberth, Kasper; Harndahl, Mikkel; Buus, Søren; Lund, Ole; Nielsen, Morten

2008-07-01

NetMHC-3.0 is trained on a large number of quantitative peptide data using both affinity data from the Immune Epitope Database and Analysis Resource (IEDB) and elution data from SYFPEITHI. The method generates high-accuracy predictions of major histocompatibility complex (MHC): peptide binding. The predictions are based on artificial neural networks trained on data from 55 MHC alleles (43 Human and 12 non-human), and position-specific scoring matrices (PSSMs) for additional 67 HLA alleles. As only the MHC class I prediction server is available, predictions are possible for peptides of length 8-11 for all 122 alleles. artificial neural network predictions are given as actual IC(50) values whereas PSSM predictions are given as a log-odds likelihood scores. The output is optionally available as download for easy post-processing. The training method underlying the server is the best available, and has been used to predict possible MHC-binding peptides in a series of pathogen viral proteomes including SARS, Influenza and HIV, resulting in an average of 75-80% confirmed MHC binders. Here, the performance is further validated and benchmarked using a large set of newly published affinity data, non-redundant to the training set. The server is free of use and available at: http://www.cbs.dtu.dk/services/NetMHC.

Net Locality

DEFF Research Database (Denmark)

de Souza e Silva, Adriana Araujo; Gordon, Eric

Provides an introduction to the new theory of Net Locality and the profound effect on individuals and societies when everything is located or locatable. Describes net locality as an emerging form of location awareness central to all aspects of digital media, from mobile phones, to Google Maps......, to location-based social networks and games, such as Foursquare and facebook. Warns of the threats these technologies, such as data surveillance, present to our sense of privacy, while also outlining the opportunities for pro-social developments. Provides a theory of the web in the context of the history...... of emerging technologies, from GeoCities to GPS, Wi-Fi, Wiki Me, and Google Android....

Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network.

Directory of Open Access Journals (Sweden)

Seung Seog Han

Full Text Available Although there have been reports of the successful diagnosis of skin disorders using deep learning, unrealistically large clinical image datasets are required for artificial intelligence (AI training. We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN trained to distinguish the nail from the background. We used R-CNN to generate training datasets of 49,567 images, which we then used to fine-tune the ResNet-152 and VGG-19 models. The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively, 125 images from Hallym University (C dataset, and 939 images from Seoul National University (D dataset. The AI (ensemble model; ResNet-152 + VGG-19 + feedforward neural networks results showed test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98, (82.7 / 96.7 / 0.95, (92.3 / 79.3 / 0.93, (87.7 / 69.3 / 0.82 for the B1, B2, C, and D datasets. With a combination of the B1 and C datasets, the AI Youden index was significantly (p = 0.01 higher than that of 42 dermatologists doing the same assessment manually. For B1+C and B2+ D dataset combinations, almost none of the dermatologists performed as well as the AI. By training with a dataset comprising 49,567 images, we achieved a diagnostic accuracy for onychomycosis using deep learning that was superior to that of most of the dermatologists who participated in this study.

Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network.