Hardware implementation of stochastic spiking neural networks.
Rosselló, Josep L; Canals, Vincent; Morro, Antoni; Oliver, Antoni
2012-08-01
Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.
A hardware implementation of neural network with modified HANNIBAL architecture
Energy Technology Data Exchange (ETDEWEB)
Lee, Bum youb; Chung, Duck Jin [Inha University, Inchon (Korea, Republic of)
1996-03-01
A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). 14 refs., 10 figs., 3 tabs.
Artificial Neural Network with Hardware Training and Hardware Refresh
Duong, Tuan A. (Inventor)
2003-01-01
A neural network circuit is provided having a plurality of circuits capable of charge storage. Also provided is a plurality of circuits each coupled to at least one of the plurality of charge storage circuits and constructed to generate an output in accordance with a neuron transfer function. Each of a plurality of circuits is coupled to one of the plurality of neuron transfer function circuits and constructed to generate a derivative of the output. A weight update circuit updates the charge storage circuits based upon output from the plurality of transfer function circuits and output from the plurality of derivative circuits. In preferred embodiments, separate training and validation networks share the same set of charge storage circuits and may operate concurrently. The validation network has a separate transfer function circuits each being coupled to the charge storage circuits so as to replicate the training network s coupling of the plurality of charge storage to the plurality of transfer function circuits. The plurality of transfer function circuits may be constructed each having a transconductance amplifier providing differential currents combined to provide an output in accordance with a transfer function. The derivative circuits may have a circuit constructed to generate a biased differential currents combined so as to provide the derivative of the transfer function.
Design of coupling resistor networks for neural network hardware
Barkan, Ozdal; Smith, W. R.; Persky, George
1990-06-01
The specification of an artificial neural network includes (1) the transformation relating each neuron's output voltage to its input voltage, and (2) a set of coupling weight factors expressing the input voltage of any neuron as a linear combination of the output voltages of other neurons. In analog VLSI chips for direct hardware implementation of these networks, neurons are often represented by amplifier elements (e.g. operational amplifiers or opamps), and resistors or active transconductances are used to couple signals from the outputs of certain neurons to the inputs of other neurons. Each coupling conductance is proportional to a single, corresponding coupling weight only under the following 'ideal' conditions: (1) each opamp has negligible output impedance, and (2) the input voltage of each opamp is developed across a low-resistance sampling resistor that is not loaded by the opamp itself. By contrast, the output impedance of a practical opamp may not be negligible in comparison to that of the high-fan network that it drives, and the sampling resistances on the opamp inputs cannot be arbitrarily low lest the input voltages be corrupted by unavoidable opamp input voltage offsets.
Hardware Prototyping of Neural Network based Fetal Electrocardiogram Extraction
Hasan, M. A.; Reaz, M. B. I.
2012-01-01
The aim of this paper is to model the algorithm for Fetal ECG (FECG) extraction from composite abdominal ECG (AECG) using VHDL (Very High Speed Integrated Circuit Hardware Description Language) for FPGA (Field Programmable Gate Array) implementation. Artificial Neural Network that provides efficient and effective ways of separating FECG signal from composite AECG signal has been designed. The proposed method gives an accuracy of 93.7% for R-peak detection in FHR monitoring. The designed VHDL model is synthesized and fitted into Altera's Stratix II EP2S15F484C3 using the Quartus II version 8.0 Web Edition for FPGA implementation.
Modular neural tile architecture for compact embedded hardware spiking neural network
Pande, Sandeep; Morgan, Fearghal; Cawley, Seamus; Bruintjes, Tom; Smit, Gerard; McGinley, Brian; Carrillo, Snaider; Harkin, Jim; McDaid, Liam
2013-01-01
Biologically-inspired packet switched network on chip (NoC) based hardware spiking neural network (SNN) architectures have been proposed as an embedded computing platform for classification, estimation and control applications. Storage of large synaptic connectivity (SNN topology) information in SNN
A hardware implementation of artificial neural networks using field programmable gate arrays
Won, E.
2007-11-01
An artificial neural network algorithm is implemented using a low-cost field programmable gate array hardware. One hidden layer is used in the feed-forward neural network structure in order to discriminate one class of patterns from the other class in real time. In this work, the training of the network is performed in the off-line computing environment and the results of the training are configured to the hardware in order to minimize the latency of the neural computation. With five 8-bit input patterns, six hidden nodes, and one 8-bit output, the implemented hardware neural network makes decisions on a set of input patterns in 11 clock cycles, or less than 200 ns with a 60 MHz clock. The result from the hardware neural computation is well predictable based on the off-line computation. This implementation may be used in level 1 hardware triggers in high energy physics experiments.
2014-01-01
In the last one decade, neural networks-based modeling has been used for computing different performance parameters of microstrip antennas because of learning and generalization features. Most of the created neural models are based on software simulation. As the neural networks show massive parallelism inherently, a parallel hardware needs to be created for creating faster computing machine by taking the advantages of the parallelism of the neural networks. This paper demonstrates a generaliz...
Directory of Open Access Journals (Sweden)
Taimoor Khan
2014-01-01
Full Text Available In the last one decade, neural networks-based modeling has been used for computing different performance parameters of microstrip antennas because of learning and generalization features. Most of the created neural models are based on software simulation. As the neural networks show massive parallelism inherently, a parallel hardware needs to be created for creating faster computing machine by taking the advantages of the parallelism of the neural networks. This paper demonstrates a generalized neural networks model created on field programmable gate array- (FPGA- based reconfigurable hardware platform for computing different performance parameters of microstrip antennas. Thus, the proposed approach provides a platform for developing low-cost neural network-based FPGA simulators for microwave applications. Also, the results obtained by this approach are in very good agreement with the measured results available in the literature.
Analyzing the scaling of connectivity in neuromorphic hardware and in models of neural networks.
Partzsch, Johannes; Schüffny, René
2011-06-01
In recent years, neuromorphic hardware systems have significantly grown in size. With more and more neurons and synapses integrated in such systems, the neural connectivity and its configurability have become crucial design constraints. To tackle this problem, we introduce a generic extended graph description of connection topologies that allows a systematical analysis of connectivity in both neuromorphic hardware and neural network models. The unifying nature of our approach enables a close exchange between hardware and models. For an existing hardware system, the optimally matched network model can be extracted. Inversely, a hardware architecture may be fitted to a particular model network topology with our description method. As a further strength, the extended graph can be used to quantify the amount of configurability for a certain network topology. This is a hardware design variable that has widely been neglected, mainly because of a missing analysis method. To condense our analysis results, we develop a classification for the scaling complexity of network models and neuromorphic hardware, based on the total number of connections and the configurability. We find a gap between several models and existing hardware, making these hardware systems either impossible or inefficient to use for scaled-up network models. In this respect, our analysis results suggest models with locality in their connections as promising approach for tackling this scaling gap.
Prezioso, M.; Merrikh-Bayat, F.; Chakrabarti, B.; Strukov, D.
2016-02-01
Artificial neural networks have been receiving increasing attention due to their superior performance in many information processing tasks. Typically, scaling up the size of the network results in better performance and richer functionality. However, large neural networks are challenging to implement in software and customized hardware are generally required for their practical implementations. In this work, we will discuss our group's recent efforts on the development of such custom hardware circuits, based on hybrid CMOS/memristor circuits, in particular of CMOL variety. We will start by reviewing the basics of memristive devices and of CMOL circuits. We will then discuss our recent progress towards demonstration of hybrid circuits, focusing on the experimental and theoretical results for artificial neural networks based on crossbarintegrated metal oxide memristors. We will conclude presentation with the discussion of the remaining challenges and the most pressing research needs.
Pfeil, Thomas; Jordan, Jakob; Tetzlaff, Tom; Grübl, Andreas; Schemmel, Johannes; Diesmann, Markus; Meier, Karlheinz
2016-04-01
High-level brain function, such as memory, classification, or reasoning, can be realized by means of recurrent networks of simplified model neurons. Analog neuromorphic hardware constitutes a fast and energy-efficient substrate for the implementation of such neural computing architectures in technical applications and neuroscientific research. The functional performance of neural networks is often critically dependent on the level of correlations in the neural activity. In finite networks, correlations are typically inevitable due to shared presynaptic input. Recent theoretical studies have shown that inhibitory feedback, abundant in biological neural networks, can actively suppress these shared-input correlations and thereby enable neurons to fire nearly independently. For networks of spiking neurons, the decorrelating effect of inhibitory feedback has so far been explicitly demonstrated only for homogeneous networks of neurons with linear subthreshold dynamics. Theory, however, suggests that the effect is a general phenomenon, present in any system with sufficient inhibitory feedback, irrespective of the details of the network structure or the neuronal and synaptic properties. Here, we investigate the effect of network heterogeneity on correlations in sparse, random networks of inhibitory neurons with nonlinear, conductance-based synapses. Emulations of these networks on the analog neuromorphic-hardware system Spikey allow us to test the efficiency of decorrelation by inhibitory feedback in the presence of hardware-specific heterogeneities. The configurability of the hardware substrate enables us to modulate the extent of heterogeneity in a systematic manner. We selectively study the effects of shared input and recurrent connections on correlations in membrane potentials and spike trains. Our results confirm that shared-input correlations are actively suppressed by inhibitory feedback also in highly heterogeneous networks exhibiting broad, heavy-tailed firing
Condition monitoring of planetary gearbox by hardware implementation of artificial neural networks
DEFF Research Database (Denmark)
Dabrowski, Dariusz
2016-01-01
-stationary conditions and are exposed to extreme events. Also bucket-wheel excavators are equipped with high-power gearboxes that are exposed to shocks. Continuous monitoring of their condition is crucial in view of early failures, and to ensure safety of exploitation. Artificial neural networks allow for a quick...... environmental conditions. In this paper, a hardware implementation of an artificial neural network designed for condition monitoring of a planetary gearbox is presented. The implementation was done on a Field Programmable Gate Array (FPGA). It is characterized by much higher efficiency and stability than...
PAX: A mixed hardware/software simulation platform for spiking neural networks.
Renaud, S; Tomas, J; Lewis, N; Bornat, Y; Daouzli, A; Rudolph, M; Destexhe, A; Saïghi, S
2010-09-01
Many hardware-based solutions now exist for the simulation of bio-like neural networks. Less conventional than software-based systems, these types of simulators generally combine digital and analog forms of computation. In this paper we present a mixed hardware-software platform, specifically designed for the simulation of spiking neural networks, using conductance-based models of neurons and synaptic connections with dynamic adaptation rules (Spike-Timing-Dependent Plasticity). The neurons and networks are configurable, and are computed in 'biological real time' by which we mean that the difference between simulated time and simulation time is guaranteed lower than 50 mus. After presenting the issues and context involved in the design and use of hardware-based spiking neural networks, we describe the analog neuromimetic integrated circuits which form the core of the platform. We then explain the organization and computation principles of the modules within the platform, and present experimental results which validate the system. Designed as a tool for computational neuroscience, the platform is exploited in collaborative research projects together with neurobiology and computer science partners.
Johnston, S P; Prasad, G; Maguire, L; McGinnity, T M
2010-12-01
This paper presents an approach that permits the effective hardware realization of a novel Evolvable Spiking Neural Network (ESNN) paradigm on Field Programmable Gate Arrays (FPGAs). The ESNN possesses a hybrid learning algorithm that consists of a Spike Timing Dependent Plasticity (STDP) mechanism fused with a Genetic Algorithm (GA). The design and implementation direction utilizes the latest advancements in FPGA technology to provide a partitioned hardware/software co-design solution. The approach achieves the maximum FPGA flexibility obtainable for the ESNN paradigm. The algorithm was applied as an embedded intelligent system robotic controller to solve an autonomous navigation and obstacle avoidance problem.
Silicon synaptic transistor for hardware-based spiking neural network and neuromorphic system
Kim, Hyungjin; Hwang, Sungmin; Park, Jungjin; Park, Byung-Gook
2017-10-01
Brain-inspired neuromorphic systems have attracted much attention as new computing paradigms for power-efficient computation. Here, we report a silicon synaptic transistor with two electrically independent gates to realize a hardware-based neural network system without any switching components. The spike-timing dependent plasticity characteristics of the synaptic devices are measured and analyzed. With the help of the device model based on the measured data, the pattern recognition capability of the hardware-based spiking neural network systems is demonstrated using the modified national institute of standards and technology handwritten dataset. By comparing systems with and without inhibitory synapse part, it is confirmed that the inhibitory synapse part is an essential element in obtaining effective and high pattern classification capability.
Implementation of neural network hardware based on a floating point operation in an FPGA
Kim, Jeong-Seob; Jung, Seul
2007-12-01
This paper presents a hardware design and implementation of the radial basis function (RBF) neural network (NN) by the hardware description language. Due to its nonlinear characteristics, it is very difficult to implement for a system with integer-based operation. To develop nonlinear functions such sigmoid functions or exponential functions, floating point operations are required. The exponential function is designed based on the 32bit single-precision floating-point format. In addition, to update weights in the network, the back-propagation algorithm is also implemented in the hardware. Most operations are performed in the floating-point based arithmetic unit and accomplished sequentially by the instruction order stored in ROM. The NN is implemented and tested on the Altera FPGA "Cyclone2 EP2C70F672C8" for nonlinear classifications.
Real-time classification of datasets with hardware embedded neuromorphic neural networks.
Bako, Laszlo
2010-05-01
Neuromorphic artificial neural networks attempt to understand the essential computations that take place in the dense networks of interconnected neurons making up the central nervous systems in living creatures. This article demonstrates that artificial spiking neural networks--built to resemble the biological model--encoding information in the timing of single spikes, are capable of computing and learning clusters from realistic data. It shows how a spiking neural network based on spike-time coding can successfully perform unsupervised and supervised clustering on real-world data. A temporal encoding procedure of continuously valued data is developed, together with a hardware implementation oriented new learning rule set. Solutions that make use of embedded soft-core microcontrollers are investigated, to implement some of the most resource-consuming components of the artificial neural network. Details of the implementations are given, with benchmark application evaluation and test bench description. Measurement results are presented, showing real-time and adaptive data processing capabilities, comparing these to related findings in the specific literature.
Directory of Open Access Journals (Sweden)
Ken Saito
2012-11-01
Full Text Available In this paper, we presented the 4.0, 2.7, 2.5 mm, width, length, height size biomimetics micro robot system which was inspired by insects. The micro robot system was made from silicon wafer fabricated by micro electro mechanical systems (MEMS technology. The mechanical system of the robot was equipped with small size rotary type actuators, link mechanisms and six legs to realize the insect‐like switching behaviour. In addition, we constructed the active hardware neural networks (HNN by analogue CMOS circuits as a locomotion controlling system. The HNN utilized the pulse‐type hardware neuron model (P‐HNM as a basic component. The HNN outputs the driving pulses using synchronization phenomena such as biological neural networks. The driving pulses can operate the actuators of the biomimetics micro robot directly. Therefore, the HNN realized the robot control without using any software programs or A/D converters. The micro robot emulated the locomotion method and the neural networks of an insect with rotary type actuators, link mechanisms and HNN. The micro robot performed forward and backward locomotion, and also changed direction by inputting an external trigger pulse. The locomotion speed was 26.4 mm/min when the step width was 0.88 mm.
Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware.
Knight, James C; Tully, Philip J; Kaplan, Bernhard A; Lansner, Anders; Furber, Steve B
2016-01-01
SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 2.0 × 104 neurons and 5.1 × 107 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately 45× more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models.
Event management for large scale event-driven digital hardware spiking neural networks.
Caron, Louis-Charles; D'Haene, Michiel; Mailhot, Frédéric; Schrauwen, Benjamin; Rouat, Jean
2013-09-01
The interest in brain-like computation has led to the design of a plethora of innovative neuromorphic systems. Individually, spiking neural networks (SNNs), event-driven simulation and digital hardware neuromorphic systems get a lot of attention. Despite the popularity of event-driven SNNs in software, very few digital hardware architectures are found. This is because existing hardware solutions for event management scale badly with the number of events. This paper introduces the structured heap queue, a pipelined digital hardware data structure, and demonstrates its suitability for event management. The structured heap queue scales gracefully with the number of events, allowing the efficient implementation of large scale digital hardware event-driven SNNs. The scaling is linear for memory, logarithmic for logic resources and constant for processing time. The use of the structured heap queue is demonstrated on a field-programmable gate array (FPGA) with an image segmentation experiment and a SNN of 65,536 neurons and 513,184 synapses. Events can be processed at the rate of 1 every 7 clock cycles and a 406×158 pixel image is segmented in 200 ms.
Karabiber, Fethullah; Vecchio, Pietro; Grassi, Giuseppe
2011-12-01
The Bio-inspired (Bi-i) Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN) paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Directory of Open Access Journals (Sweden)
Vecchio Pietro
2011-01-01
Full Text Available Abstract The Bio-inspired (Bi-i Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Carrillo, Snaider; Harkin, Jim; McDaid, Liam; Pande, Sandeep; Cawley, Seamus; McGinley, Brian; Morgan, Fearghal
2012-09-01
The brain is highly efficient in how it processes information and tolerates faults. Arguably, the basic processing units are neurons and synapses that are interconnected in a complex pattern. Computer scientists and engineers aim to harness this efficiency and build artificial neural systems that can emulate the key information processing principles of the brain. However, existing approaches cannot provide the dense interconnect for the billions of neurons and synapses that are required. Recently a reconfigurable and biologically inspired paradigm based on network-on-chip (NoC) and spiking neural networks (SNNs) has been proposed as a new method of realising an efficient, robust computing platform. However, the use of the NoC as an interconnection fabric for large-scale SNNs demands a good trade-off between scalability, throughput, neuron/synapse ratio and power consumption. This paper presents a novel traffic-aware, adaptive NoC router, which forms part of a proposed embedded mixed-signal SNN architecture called EMBRACE (EMulating Biologically-inspiRed ArChitectures in hardwarE). The proposed adaptive NoC router provides the inter-neuron connectivity for EMBRACE, maintaining router communication and avoiding dropped router packets by adapting to router traffic congestion. Results are presented on throughput, power and area performance analysis of the adaptive router using a 90 nm CMOS technology which outperforms existing NoCs in this domain. The adaptive behaviour of the router is also verified on a Stratix II FPGA implementation of a 4 × 2 router array with real-time traffic congestion. The presented results demonstrate the feasibility of using the proposed adaptive NoC router within the EMBRACE architecture to realise large-scale SNNs on embedded hardware.
Hotta, Hirohisa; Murahashi, Yoshimitsu; Doki, Shinji; Okuma, Shigeru
In order to ride on the strength of paralell operation a feature of neural network, it is preferable that all neuron is implemented on hardware. Formerly, we combine Neural Network and ΔΣ modulation, which is a method of converting to 1bit pulsed signal. Then we succeeded to configurate “a Pulsed Neural Network based on ΔΣ modulation(DSM-PNN)", which keep the circuit scale as same as to operate precisely. In last paper, we proposed hardware implementation methods of DSM-PNN with GHA learning rule and show its availability in linear operation. However, since neural networks are characterized by nonlinear map, signals needs to be treated with sufficient precision, also in nonlinear operation. In this paper, in order to shows that the 1-bit signal processing by DSM-PNN can be available, even when it includes nonlinear operation, we proposed the technique of realizing algorithm of ICA including nonlinear operation in DSM-PNN and confirm the performance of it.
Sign Language Recognition System using Neural Network for Digital Hardware Implementation
Vargas, Lorena P.; Barba, Leiner; Torres, C. O.; Mattos, L.
2011-01-01
This work presents an image pattern recognition system using neural network for the identification of sign language to deaf people. The system has several stored image that show the specific symbol in this kind of language, which is employed to teach a multilayer neural network using a back propagation algorithm. Initially, the images are processed to adapt them and to improve the performance of discriminating of the network, including in this process of filtering, reduction and elimination noise algorithms as well as edge detection. The system is evaluated using the signs without including movement in their representation.
Zoev, I. V.; Beresnev, A. P.; Mytsko, E. A.; Malchukov, A. N.
2017-02-01
An important aspect of modern automation is machine learning. Specifically, neural networks are used for environment analysis and decision making based on available data. This article covers the most frequently performed operations on floating-point numbers in artificial neural networks. Also, a selection of the optimum value of the bit to 14-bit floating-point numbers for implementation on FPGAs was submitted based on the modern architecture of integrated circuits. The description of the floating-point multiplication (multiplier) algorithm was presented. In addition, features of the addition (adder) and subtraction (subtractor) operations were described in the article. Furthermore, operations for such variety of neural networks as a convolution network - mathematical comparison of a floating point (‘less than’ and ‘greater than or equal’) were presented. In conclusion, the comparison with calculating units of Atlera was made.
Standard Cell-Based Implementation of a Digital Optoelectronic Neural-Network Hardware
Maier, Klaus D.; Beckstein, Clemens; Blickhan, Reinhard; Erhard, Werner
2001-03-01
A standard cell-based implementation of a digital optoelectronic neural-network architecture is presented. The overall structure of the multilayer perceptron network that was used, the optoelectronic interconnection system between the layers, and all components required in each layer are defined. The design process from VHDL-based modeling from synthesis and partly automatic placing and routing to the final editing of one layer of the circuit of the multilayer perceptrons are described. A suitable approach for the standard cell-based design of optoelectronic systems is presented, and shortcomings of the design tool that was used are pointed out. The layout for the microelectronic circuit of one layer in a multilayer perceptron neural network with a performance potential 1 magnitude higher than neural networks that are purely electronic based has been successfully designed.
FPGA Implementations of Feed Forward Neural Network by using Floating Point Hardware Accelerators
Directory of Open Access Journals (Sweden)
Gabriele-Maria Lozito
2014-01-01
Full Text Available This paper documents the research towards the analysis of different solutions to implement a Neural Network architecture on a FPGA design by using floating point accelerators. In particular, two different implementations are investigated: a high level solution to create a neural network on a soft processor design, with different strategies for enhancing the performance of the process; a low level solution, achieved by a cascade of floating point arithmetic elements. Comparisons of the achieved performance in terms of both time consumptions and FPGA resources employed for the architectures are presented.
Comparison of GPU- and CPU-implementations of mean-firing rate neural networks on parallel hardware.
Dinkelbach, Helge Ülo; Vitay, Julien; Beuth, Frederik; Hamker, Fred H
2012-01-01
Modern parallel hardware such as multi-core processors (CPUs) and graphics processing units (GPUs) have a high computational power which can be greatly beneficial to the simulation of large-scale neural networks. Over the past years, a number of efforts have focused on developing parallel algorithms and simulators best suited for the simulation of spiking neural models. In this article, we aim at investigating the advantages and drawbacks of the CPU and GPU parallelization of mean-firing rate neurons, widely used in systems-level computational neuroscience. By comparing OpenMP, CUDA and OpenCL implementations towards a serial CPU implementation, we show that GPUs are better suited than CPUs for the simulation of very large networks, but that smaller networks would benefit more from an OpenMP implementation. As this performance strongly depends on data organization, we analyze the impact of various factors such as data structure, memory alignment and floating precision. We then discuss the suitability of the different hardware depending on the networks' size and connectivity, as random or sparse connectivities in mean-firing rate networks tend to break parallel performance on GPUs due to the violation of coalescence.
Fixed latency on-chip interconnect for hardware spiking neural network architectures
Pande, Sandeep; Morgan, Fearghal; Smit, Gerard; Bruintjes, Tom; Rutgers, Jochem; Cawley, Seamus; Harkin, Jim; McDaid, Liam
2013-01-01
Information in a Spiking Neural Network (SNN) is encoded as the relative timing between spikes. Distortion in spike timings can impact the accuracy of SNN operation by modifying the precise firing time of neurons within the SNN. Maintaining the integrity of spike timings is crucial for reliable oper
González, M.; Lamela, H.; Jiménez, M.; Gimeno, J.; Ruiz-Llata, M.
2007-04-01
In this paper we present the scheme for a control circuit used in an image processing system which is to be implemented in a neural network which has a high level of connectivity and reconfiguration of neurons for integration and trigger based on the Address-Event Representation. This scheme will be employed as a pre-processing stage for a vision system which employs as its core processing an Optical Broadcast Neural Network (OBNN). [Optical Engineering letters 42 (9), 2488(2003)]. The proposed vision system allows the possibility to introduce patterns from any acquisition system of images, for posterior processing.
2012-11-01
and power (SWaP); radial basis function; zero instruction set computing (ZISC); pattern recognition 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF...perception and classification problems historically difficult for traditional, von Neumann-based computers. The neuromorphic community was...Manhattan method or the Lsup method. In the Manhattan method, , 1 ∑ = −= n i iiMan PVD (1) Figure 1: Neural Network Diagram. Each input node
Mahdiani, Hamid Reza; Fakhraie, Sied Mehdi; Lucas, Caro
2012-08-01
Reliability should be identified as the most important challenge in future nano-scale very large scale integration (VLSI) implementation technologies for the development of complex integrated systems. Normally, fault tolerance (FT) in a conventional system is achieved by increasing its redundancy, which also implies higher implementation costs and lower performance that sometimes makes it even infeasible. In contrast to custom approaches, a new class of applications is categorized in this paper, which is inherently capable of absorbing some degrees of vulnerability and providing FT based on their natural properties. Neural networks are good indicators of imprecision-tolerant applications. We have also proposed a new class of FT techniques called relaxed fault-tolerant (RFT) techniques which are developed for VLSI implementation of imprecision-tolerant applications. The main advantage of RFT techniques with respect to traditional FT solutions is that they exploit inherent FT of different applications to reduce their implementation costs while improving their performance. To show the applicability as well as the efficiency of the RFT method, the experimental results for implementation of a face-recognition computationally intensive neural network and its corresponding RFT realization are presented in this paper. The results demonstrate promising higher performance of artificial neural network VLSI solutions for complex applications in faulty nano-scale implementation environments.
Autonomous target tracking of UAVs based on low-power neural network hardware
Yang, Wei; Jin, Zhanpeng; Thiem, Clare; Wysocki, Bryant; Shen, Dan; Chen, Genshe
2014-05-01
Detecting and identifying targets in unmanned aerial vehicle (UAV) images and videos have been challenging problems due to various types of image distortion. Moreover, the significantly high processing overhead of existing image/video processing techniques and the limited computing resources available on UAVs force most of the processing tasks to be performed by the ground control station (GCS) in an off-line manner. In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate novel processing paradigms that can fulfill the real-time processing requirements, while fitting the size, weight, and power (SWaP) constrained environment. In this paper, we present a new autonomous target identification approach on UAVs, leveraging the emerging neuromorphic hardware which is capable of massively parallel pattern recognition processing and demands only a limited level of power consumption. A proof-of-concept prototype was developed based on a micro-UAV platform (Parrot AR Drone) and the CogniMemTMneural network chip, for processing the video data acquired from a UAV camera on the y. The aim of this study was to demonstrate the feasibility and potential of incorporating emerging neuromorphic hardware into next-generation UAVs and their superior performance and power advantages towards the real-time, autonomous target tracking.
Optimization of a hardware implementation for pulse coupled neural networks for image applications
Gimeno Sarciada, Jesús; Lamela Rivera, Horacio; Warde, Cardinal
2010-04-01
Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.
Chen, Jun; Shibata, Tadashi
2007-04-01
Pulse-coupled neural networks (PCNNs) are biologically inspired algorithms that have been shown to be highly effective for image feature generation. However, conventional PCNNs are software-oriented algorithms that are too complicated to implement as very-large-scale integration (VLSI) hardware. To employ PCNNs in image-feature-generation VLSIs, a hardware-implementation-friendly PCNN is proposed here. By introducing the concepts of exponentially decaying output and a one-branch dendritic tree, the new PCNN eliminates the large number of convolution operators and floating-point multipliers in conventional PCNNs without compromising its performance at image feature generation. As an analog VLSI implementation of the new PCNN, an image-feature-generation circuit is proposed. By employing floating-gate metal-oxide-semiconductor (MOS) technology, the circuit achieves a full voltage-mode implementation of the PCNN in a compact structure. Inheriting the merits of the PCNN, the circuit is capable of generating rotation-independent and translation-independent features for input patterns, which has been verified by SPICE simulation.
Mitchell, Kyle; Ebel, William J.; Watkins, Steve E.
2009-11-01
Artificial neural networks are studied for use in estimating strain in extrinsic Fabry-Pérot interferometric sensors. These networks can require large memory spaces and a large number of calculations for implementation. We describe a modified neural network solution that is suitable for implementation on relatively low cost, low-power hardware. Moreover, we give strain estimates resulting from an implementation of the artificial neural network algorithm on an 8-bit 8051 processor with 64 kbytes of memory. For example, one of our results shows that for 2048 samples of the transmittance signal, the presented neural network algorithm requires around 24,622 floating point multiplies and 35,835 adds, and where the data and algorithm fit within the 64-kbyte memory.
A new wide range Euclidean distance circuit for neural network hardware implementations.
Gopalan, A; Titus, A H
2003-01-01
In this paper, we describe an analog very large-scale integration (VLSI) implementation of a wide range Euclidean distance computation circuit - the key element of many synapse circuits. This circuit is essentially a wide-range absolute value circuit that is designed to be as small as possible (80 /spl times/ 76 /spl mu/m) in order to achieve maximum synapse density while maintaining a wide range of operation (0.5 to 4.5 V) and low power consumption (less than 200 /spl mu/W). The circuit has been fabricated in 1.5-/spl mu/m technology through MOSIS. We present simulated and experimental results of the circuit, and compare these results. Ultimately, this circuit is intended for use as part of a high-density hardware implementation of a self-organizing map (SOM). We describe how this circuit can be used as part of the SOM and how the SOM is going to be used as part of a larger bio-inspired vision system based on the octopus visual system.
Wang, I.-Ting; Chang, Chih-Cheng; Chiu, Li-Wen; Chou, Teyuh; Hou, Tuo-Hung
2016-09-01
The implementation of highly anticipated hardware neural networks (HNNs) hinges largely on the successful development of a low-power, high-density, and reliable analog electronic synaptic array. In this study, we demonstrate a two-layer Ta/TaO x /TiO2/Ti cross-point synaptic array that emulates the high-density three-dimensional network architecture of human brains. Excellent uniformity and reproducibility among intralayer and interlayer cells were realized. Moreover, at least 50 analog synaptic weight states could be precisely controlled with minimal drifting during a cycling endurance test of 5000 training pulses at an operating voltage of 3 V. We also propose a new state-independent bipolar-pulse-training scheme to improve the linearity of weight updates. The improved linearity considerably enhances the fault tolerance of HNNs, thus improving the training accuracy.
Modular, Hierarchical Learning By Artificial Neural Networks
Baldi, Pierre F.; Toomarian, Nikzad
1996-01-01
Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.
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.
Directory of Open Access Journals (Sweden)
Schwindling Jerome
2010-04-01
Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.
Neural networks for triggering
Energy Technology Data Exchange (ETDEWEB)
Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))
1990-01-01
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.
Vonk, E.; Jain, L.C.; Veelenturf, L.P.J.
1995-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Rostro-Gonzalez, Horacio; Cessac, Bruno; Girau, Bernard; Torres-Huitzil, Cesar
2011-01-01
This paper presents a numerical analysis of the role of asymptotic dynamics in the design of hardware-based implementations of the generalised integrate-and-fire (gIF) neuron models. These proposed implementations are based on extensions of the discrete-time spiking neuron model, which was introduced by Soula et al., and have been implemented on Field Programmable Gate Array (FPGA) devices using fixed-point arithmetic. Mathematical studies conducted by Cessac have evidenced the existence of three main regimes (neural death, periodic and chaotic regimes) in the activity of such neuron models. These activity regimes are characterised in hardware by considering a precision analysis in the design of an architecture for an FPGA-based implementation. The proposed approach, although based on gIF neuron models and FPGA hardware, can be extended to more complex neuron models as well as to different in silico implementations.
Campus Information Network Hardware System Design%Campus Information Network Hardware System Design
Institute of Scientific and Technical Information of China (English)
刘正勇
2011-01-01
The emphasis of constructing and developing the campus information network is how to design and optimize the network hardware system. This paper mainly studies the network system structure design, the server system structure design and the network export
ANNarchy: a code generation approach to neural simulations on parallel hardware
Directory of Open Access Journals (Sweden)
Julien eVitay
2015-07-01
Full Text Available Many modern neural simulators focus on the simulation of networks of spiking neurons on parallel hardware. Another important framework in computational neuroscience, rate-coded neural networks, is mostly difficult or impossible to implement using these simulators. We present here the ANNarchy (Artificial Neural Networks architect neural simulator, which allows to easily define and simulate rate-coded and spiking networks, as well as combinations of both. The interface in Python has been designed to be close to the PyNN interface, while the definition of neuron and synapse models can be specified using an equation-oriented mathematical description similar to the Brian neural simulator. This information is used to generate C++ code that will efficiently perform the simulation on the chosen parallel hardware (multi-core system or graphical processing unit. Several numerical methods are available to transform ordinary differential equations into an efficient C++ code. We compare the parallel performance of the simulator to existing solutions.
ANNarchy: a code generation approach to neural simulations on parallel hardware.
Vitay, Julien; Dinkelbach, Helge Ü; Hamker, Fred H
2015-01-01
Many modern neural simulators focus on the simulation of networks of spiking neurons on parallel hardware. Another important framework in computational neuroscience, rate-coded neural networks, is mostly difficult or impossible to implement using these simulators. We present here the ANNarchy (Artificial Neural Networks architect) neural simulator, which allows to easily define and simulate rate-coded and spiking networks, as well as combinations of both. The interface in Python has been designed to be close to the PyNN interface, while the definition of neuron and synapse models can be specified using an equation-oriented mathematical description similar to the Brian neural simulator. This information is used to generate C++ code that will efficiently perform the simulation on the chosen parallel hardware (multi-core system or graphical processing unit). Several numerical methods are available to transform ordinary differential equations into an efficient C++code. We compare the parallel performance of the simulator to existing solutions.
VLSI implementation of neural networks.
Wilamowski, B M; Binfet, J; Kaynak, M O
2000-06-01
Currently, fuzzy controllers are the most popular choice for hardware implementation of complex control surfaces because they are easy to design. Neural controllers are more complex and hard to train, but provide an outstanding control surface with much less error than that of a fuzzy controller. There are also some problems that have to be solved before the networks can be implemented on VLSI chips. First, an approximation function needs to be developed because CMOS neural networks have an activation function different than any function used in neural network software. Next, this function has to be used to train the network. Finally, the last problem for VLSI designers is the quantization effect caused by discrete values of the channel length (L) and width (W) of MOS transistor geometries. Two neural networks were designed in 1.5 microm technology. Using adequate approximation functions solved the problem of activation function. With this approach, trained networks were characterized by very small errors. Unfortunately, when the weights were quantized, errors were increased by an order of magnitude. However, even though the errors were enlarged, the results obtained from neural network hardware implementations were superior to the results obtained with fuzzy system approach.
Energy Technology Data Exchange (ETDEWEB)
Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)
1996-12-31
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
Constructive neural network learning
Lin, Shaobo; Zeng, Jinshan; Zhang, Xiaoqin
2016-01-01
In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive feed-forward neural network (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for FNN approximation, but also ...
Generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2013-03-01
In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They are input, pattern, summation, normalization and output layers. In addition to topological difference, the proposed neural network has gradient descent based optimization of smoothing parameter approach and diverge effect term added calculation improvements. Diverge effect term is an improvement on summation layer calculation to supply additional separation ability and flexibility. Performance of generalized classifier neural network is compared with that of the probabilistic neural network, multilayer perceptron algorithm and radial basis function neural network on 9 different data sets and with that of generalized regression neural network on 3 different data sets include only two classes in MATLAB environment. Better classification performance up to %89 is observed. Improved classification performances proved the effectivity of the proposed neural network.
Chaotic diagonal recurrent neural network
Institute of Scientific and Technical Information of China (English)
Wang Xing-Yuan; Zhang Yi
2012-01-01
We propose a novel neural network based on a diagonal recurrent neural network and chaos,and its structure andlearning algorithm are designed.The multilayer feedforward neural network,diagonal recurrent neural network,and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map.The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.
Chung-Ming Kuan
2006-01-01
Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods.
Institute of Scientific and Technical Information of China (English)
程丹; 王连明
2011-01-01
为了充分发挥人工神经网络所具有的并行计算、分布式存储的优点,提出了将NIOSⅡ多核技术应用于Hopfield神经网络硬件实现的方法.采用中断方式和SDRAM实现多核之间的通信,并将所实现的硬件用于数字识别,验证了多核通信方法应用于神经网络硬件实现的有效性和可行性.%To take advantage of the parallel computing and distributed storage characteristics of Neural network, NIOS Ⅱ multi-core technology is used to implement the hardware of Hopfield neural network. The method uses interrupt and SDRAM to realize the communication between NIOS Ⅱ multi-cores. Then, the implemented Hopfield network is used for digital number identification. The effectiveness and feasibility of this method are proved.
Neural Networks: Implementations and Applications
Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.
1996-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Neural Networks: Implementations and Applications
Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.
1996-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Fiber optic Adaline neural networks
Ghosh, Anjan K.; Trepka, Jim; Paparao, Palacharla
1993-02-01
Optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators has been discussed recently. We describe the design of a single layer fiber optic Adaline neural network which can be used as a bit pattern classifier. In our realization we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The new optical neural network described in this paper is designed for optical processing of guided lightwave signals, not electronic signals. We analyzed the convergence or learning characteristics of the optically implemented Adaline in the presence of errors in the hardware, and we studied methods for improving the convergence rate of the Adaline.
DEFF Research Database (Denmark)
Krogh, Anders Stærmose; Riis, Søren Kamaric
1999-01-01
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...
Learning in Neural Networks: VLSI Implementation Strategies
Duong, Tuan Anh
1995-01-01
Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.
DEFF Research Database (Denmark)
Hansen, Lars Kai; Salamon, Peter
1990-01-01
We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....
Critical Branching Neural Networks
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Critical Branching Neural Networks
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Ultra-low noise miniaturized neural amplifier with hardware averaging
Dweiri, Yazan M.; Eggers, Thomas; McCallum, Grant; Durand, Dominique M.
2015-08-01
Objective. Peripheral nerves carry neural signals that could be used to control hybrid bionic systems. Cuff electrodes provide a robust and stable interface but the recorded signal amplitude is small (amplifier should add as little noise as possible. Since mainstream neural amplifiers have a baseline noise of 2 μVrms or higher, novel designs are required. Approach. Here we apply the concept of hardware averaging to nerve recordings obtained with cuff electrodes. An optimization procedure is developed to minimize noise and power simultaneously. The novel design was based on existing neural amplifiers (Intan Technologies, LLC) and is validated with signals obtained from the FINE in chronic dog experiments. Main results. We showed that hardware averaging leads to a reduction in the total recording noise by a factor of 1/√N or less depending on the source resistance. Chronic recording of physiological activity with FINE using the presented design showed significant improvement on the recorded baseline noise with at least two parallel operation transconductance amplifiers leading to a 46.1% reduction at N = 8. The functionality of these recordings was quantified by the SNR improvement and shown to be significant for N = 3 or more. The present design was shown to be capable of generating amplifier. Significance. These results demonstrate the efficacy of hardware averaging on noise improvement for neural recording with cuff electrodes, and can accommodate the presence of high source impedances that are associated with the miniaturized contacts and the high channel count in electrode arrays. This technique can be adopted for other applications where miniaturized and implantable multichannel acquisition systems with ultra-low noise and low power are required.
Neural networks and graph theory
Institute of Scientific and Technical Information of China (English)
许进; 保铮
2002-01-01
The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.
Parallel and Mixed Hardware Implementation of Artificial Neuron Network on the FPGA Platform
Directory of Open Access Journals (Sweden)
ATIBI Mohamed
2014-10-01
Full Text Available Most applications in different fields (automotive, robotics, medical… take advantage of the proven performance by artificial neural networks to solve their most complex problems. The architecture chosen for implementation is the multilayer perceptron that uses retro propagation as a learning algorithm. This article presents modular hardware implementation of multilayer perceptron architecture of artificial neuron network ‘ANN’, in the FPGA platform according to two models (parallel and mixed hardware implementation, and the comparison between these two implementations in terms of hardware resources and execution time. The two implementations are based on the proposed module of a formal neuron with the sigmoid activation function.
Neural networks in seismic discrimination
Energy Technology Data Exchange (ETDEWEB)
Dowla, F.U.
1995-01-01
Neural networks are powerful and elegant computational tools that can be used in the analysis of geophysical signals. At Lawrence Livermore National Laboratory, we have developed neural networks to solve problems in seismic discrimination, event classification, and seismic and hydrodynamic yield estimation. Other researchers have used neural networks for seismic phase identification. We are currently developing neural networks to estimate depths of seismic events using regional seismograms. In this paper different types of network architecture and representation techniques are discussed. We address the important problem of designing neural networks with good generalization capabilities. Examples of neural networks for treaty verification applications are also described.
Institute of Scientific and Technical Information of China (English)
赵毅强; 刘沈丰; 何家骥; 杨松
2016-01-01
针对目前硬件木马的侧信道检测普遍采用基于降维与主特征提取的分类方法，该方法在选取有用信息过程中可能会损失包含木马特征的关键信息这一问题，提出了一种基于自组织竞争神经网络的硬件木马检测方法．该方法在不损失有用信息的基础上，采用无监督学习的方式建立数学模型，对母本信息与待测信息进行分类判别．基于FPGA搭建了验证系统并对侧信道电流信息进行采集．数据处理结果表明：该方法可以有效检测出占母本电路面积0．16％的硬件木马．%Nowadays the most commonly used method for side channel hardware Trojan detection is dimensionality reduction and main feature extraction .The disadvantage is that it may lose critical in‐formation about Trojan features while selecting useful information .To solve this problem ,a Trojan detection method based on self‐organizing competition neural network was proposed .The proposed method utilized unsupervised learning ways to build mathematical models for classification and dis‐crimination between golden information and testing information .A verification system was set up based on FPGA (field‐programmable gate array ) to acquire side channel current information .Testing result shows that the proposed method can effectively detect hardware Trojan accounting an area less than 0 .16% of the golden circuit .
Fuzzy Multiresolution Neural Networks
Ying, Li; Qigang, Shang; Na, Lei
A fuzzy multi-resolution neural network (FMRANN) based on particle swarm algorithm is proposed to approximate arbitrary nonlinear function. The active function of the FMRANN consists of not only the wavelet functions, but also the scaling functions, whose translation parameters and dilation parameters are adjustable. A set of fuzzy rules are involved in the FMRANN. Each rule either corresponding to a subset consists of scaling functions, or corresponding to a sub-wavelet neural network consists of wavelets with same dilation parameters. Incorporating the time-frequency localization and multi-resolution properties of wavelets with the ability of self-learning of fuzzy neural network, the approximation ability of FMRANN can be remarkable improved. A particle swarm algorithm is adopted to learn the translation and dilation parameters of the wavelets and adjusting the shape of membership functions. Simulation examples are presented to validate the effectiveness of FMRANN.
Rule Extraction:Using Neural Networks or for Neural Networks?
Institute of Scientific and Technical Information of China (English)
Zhi-Hua Zhou
2004-01-01
In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.
A Comparative Study on Hardware Platforms for Wireless Sensor Networks
Directory of Open Access Journals (Sweden)
Thang Vu Chien
2012-01-01
Full Text Available Recently, Wireless Sensor Networks (WSNs attract a great deal of research attention, and are envisioned to support a variety of applications, including building monitoring, environment control, wild-life habitat monitoring, forest fire detection, industry automation, military, security, and health-care. Over the years, we have seen a variety of hardware platforms for WSNs to facilitate developing WSN applications. In this paper, we provide a comprehensive review of existing hardware platforms for WSNs. We ﬁrst present the hardware architecture of a wireless sensor node. We then survey the major hardware platforms for WSNs and present a comparison of these hardware platforms. Finally we present some recommendations from the perspectives of hardware platform developers and hardware platform users. The authors hope that making information about existing hardware platforms will assist researchers working in this area to appreciate the diversity of platforms available to them and to help them select the most appropriate platform for their purposes.
Introduction to Artificial Neural Networks
DEFF Research Database (Denmark)
Larsen, Jan
1999-01-01
The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....
Compressing Convolutional Neural Networks
Chen, Wenlin; Wilson, James T.; Tyree, Stephen; Weinberger, Kilian Q.; Chen, Yixin
2015-01-01
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected laye...
Artificial neural network modelling
Samarasinghe, Sandhya
2016-01-01
This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .
Critical branching neural networks.
Kello, Christopher T
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical branching and, in doing so, simulates observed scaling laws as pervasive to neural and behavioral activity. These scaling laws are related to neural and cognitive functions, in that critical branching is shown to yield spiking activity with maximal memory and encoding capacities when analyzed using reservoir computing techniques. The model is also shown to account for findings of pervasive 1/f scaling in speech and cued response behaviors that are difficult to explain by isolable causes. Issues and questions raised by the model and its results are discussed from the perspectives of physics, neuroscience, computer and information sciences, and psychological and cognitive sciences.
Design of FPGA Based Neural Network Controller for Earth Station Power System
Dorrah, Hassen T.; Ninet M. A. El-Rahman; Faten H. Fahmy; Hanaa T. El-madany
2012-01-01
Automation of generating hardware description language code from neural networks models can highly decrease time of implementation those networks into a digital devices, thus significant money savings. To implement the neural network into hardware designer, it is required to translate generated model into device structure. VHDL language is used to describe those networks into hardware. VHDL code has been proposed to implement ANNs as well as to present simulation results with floating point a...
Generalized Adaptive Artificial Neural Networks
Tawel, Raoul
1993-01-01
Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.
Gupta, S; Gupta, Sanjay
2002-01-01
This paper initiates the study of quantum computing within the constraints of using a polylogarithmic ($O(\\log^k n), k\\geq 1$) number of qubits and a polylogarithmic number of computation steps. The current research in the literature has focussed on using a polynomial number of qubits. A new mathematical model of computation called \\emph{Quantum Neural Networks (QNNs)} is defined, building on Deutsch's model of quantum computational network. The model introduces a nonlinear and irreversible gate, similar to the speculative operator defined by Abrams and Lloyd. The precise dynamics of this operator are defined and while giving examples in which nonlinear Schr\\"{o}dinger's equations are applied, we speculate on its possible implementation. The many practical problems associated with the current model of quantum computing are alleviated in the new model. It is shown that QNNs of logarithmic size and constant depth have the same computational power as threshold circuits, which are used for modeling neural network...
Interval probabilistic neural network.
Kowalski, Piotr A; Kulczycki, Piotr
2017-01-01
Automated classification systems have allowed for the rapid development of exploratory data analysis. Such systems increase the independence of human intervention in obtaining the analysis results, especially when inaccurate information is under consideration. The aim of this paper is to present a novel approach, a neural networking, for use in classifying interval information. As presented, neural methodology is a generalization of probabilistic neural network for interval data processing. The simple structure of this neural classification algorithm makes it applicable for research purposes. The procedure is based on the Bayes approach, ensuring minimal potential losses with regard to that which comes about through classification errors. In this article, the topological structure of the network and the learning process are described in detail. Of note, the correctness of the procedure proposed here has been verified by way of numerical tests. These tests include examples of both synthetic data, as well as benchmark instances. The results of numerical verification, carried out for different shapes of data sets, as well as a comparative analysis with other methods of similar conditioning, have validated both the concept presented here and its positive features.
Directory of Open Access Journals (Sweden)
Kapil Nahar
2012-12-01
Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information.The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems.Ann’s, like people, learn by example.
Directory of Open Access Journals (Sweden)
Kapil Nahar
2012-12-01
Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.
VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK
African Journals Online (AJOL)
VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK: A CASE STUDY OF RUMUOLA DISTRIBUTION NETWORK. ... The artificial neural networks controller engaged to controlling the dynamic voltage ... Article Metrics.
Trimaran Resistance Artificial Neural Network
2011-01-01
11th International Conference on Fast Sea Transportation FAST 2011, Honolulu, Hawaii, USA, September 2011 Trimaran Resistance Artificial Neural Network Richard...Trimaran Resistance Artificial Neural Network 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e... Artificial Neural Network and is restricted to the center and side-hull configurations tested. The value in the parametric model is that it is able to
[Artificial neural networks in Neurosciences].
Porras Chavarino, Carmen; Salinas Martínez de Lecea, José María
2011-11-01
This article shows that artificial neural networks are used for confirming the relationships between physiological and cognitive changes. Specifically, we explore the influence of a decrease of neurotransmitters on the behaviour of old people in recognition tasks. This artificial neural network recognizes learned patterns. When we change the threshold of activation in some units, the artificial neural network simulates the experimental results of old people in recognition tasks. However, the main contributions of this paper are the design of an artificial neural network and its operation inspired by the nervous system and the way the inputs are coded and the process of orthogonalization of patterns.
Directory of Open Access Journals (Sweden)
J. Reyes-Reyes
2000-01-01
Full Text Available In this paper, an adaptive technique is suggested to provide the passivity property for a class of partially known SISO nonlinear systems. A simple Dynamic Neural Network (DNN, containing only two neurons and without any hidden-layers, is used to identify the unknown nonlinear system. By means of a Lyapunov-like analysis the new learning law for this DNN, guarantying both successful identification and passivation effects, is derived. Based on this adaptive DNN model, an adaptive feedback controller, serving for wide class of nonlinear systems with an a priori incomplete model description, is designed. Two typical examples illustrate the effectiveness of the suggested approach.
Fast implementation of neural network classification
Seo, Guiwon; Ok, Jiheon; Lee, Chulhee
2013-09-01
Most artificial neural networks use a nonlinear activation function that includes sigmoid and hyperbolic tangent functions. Most artificial networks employ nonlinear functions such as these sigmoid and hyperbolic tangent functions, which incur high complexity costs, particularly during hardware implementation. In this paper, we propose new polynomial approximation methods for nonlinear activation functions that can substantially reduce complexity without sacrificing performance. The proposed approximation methods were applied to pattern classification problems. Experimental results show that the processing time was reduced by up to 50% without any performance degradations in terms of computer simulation.
Heiden, Uwe
1980-01-01
The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica ted throughout the text. However, they are not explored in de tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be havior of neurons or neuron pools. In this respect the essay is writt...
Neural Networks for Optimal Control
DEFF Research Database (Denmark)
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
Neural Networks for Optimal Control
DEFF Research Database (Denmark)
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
Dimensionality reduction in conic section function neural network
Indian Academy of Sciences (India)
Tulay Yildirim; Lale Ozyilmaz
2002-12-01
This paper details how dimensionality can be reduced in conic section function neural networks (CSFNN). This is particularly important for hardware implementation of networks. One of the main problems to be solved when considering the hardware design is the high connectivity requirement. If the effect that each of the network inputs has on the network output after training a neural network is known, then some inputs can be removed from the network. Consequently, the dimensionality of the network, and hence, the connectivity and the training time can be reduced. Sensitivity analysis, which extracts the cause and effect relationship between the inputs and outputs of the network, has been proposed as a method to achieve this and is investigated for Iris plant, thyroid disease and ionosphere databases. Simulations demonstrate the validity of the method used.
The next generation of neural network chips
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.
1997-08-01
There have been many national and international neural networks research initiatives: USA (DARPA, NIBS), Canada (IRIS), Japan (HFSP) and Europe (BRAIN, GALA TEA, NERVES, ELENE NERVES 2) -- just to mention a few. Recent developments in the field of neural networks, cognitive science, bioengineering and electrical engineering have made it possible to understand more about the functioning of large ensembles of identical processing elements. There are more research papers than ever proposing solutions and hardware implementations are by no means an exception. Two fields (computing and neuroscience) are interacting in ways nobody could imagine just several years ago, and -- with the advent of new technologies -- researchers are focusing on trying to copy the Brain. Such an exciting confluence may quite shortly lead to revolutionary new computers and it is the aim of this invited session to bring to light some of the challenging research aspects dealing with the hardware realizability of future intelligent chips. Present-day (conventional) technology is (still) mostly digital and, thus, occupies wider areas and consumes much more power than the solutions envisaged. The innovative algorithmic and architectural ideals should represent important breakthroughs, paving the way towards making neural network chips available to the industry at competitive prices, in relatively small packages and consuming a fraction of the power required by equivalent digital solutions.
Tagliaferri, Roberto; Longo, Giuseppe; Milano, Leopoldo; Acernese, Fausto; Barone, Fabrizio; Ciaramella, Angelo; De Rosa, Rosario; Donalek, Ciro; Eleuteri, Antonio; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, Alfredo
2003-01-01
In the last decade, the use of neural networks (NN) and of other soft computing methods has begun to spread also in the astronomical community which, due to the required accuracy of the measurements, is usually reluctant to use automatic tools to perform even the most common tasks of data reduction and data mining. The federation of heterogeneous large astronomical databases which is foreseen in the framework of the astrophysical virtual observatory and national virtual observatory projects, is, however, posing unprecedented data mining and visualization problems which will find a rather natural and user friendly answer in artificial intelligence tools based on NNs, fuzzy sets or genetic algorithms. This review is aimed to both astronomers (who often have little knowledge of the methodological background) and computer scientists (who often know little about potentially interesting applications), and therefore will be structured as follows: after giving a short introduction to the subject, we shall summarize the methodological background and focus our attention on some of the most interesting fields of application, namely: object extraction and classification, time series analysis, noise identification, and data mining. Most of the original work described in the paper has been performed in the framework of the AstroNeural collaboration (Napoli-Salerno).
Logic Mining Using Neural Networks
Sathasivam, Saratha
2008-01-01
Knowledge could be gained from experts, specialists in the area of interest, or it can be gained by induction from sets of data. Automatic induction of knowledge from data sets, usually stored in large databases, is called data mining. Data mining methods are important in the management of complex systems. There are many technologies available to data mining practitioners, including Artificial Neural Networks, Regression, and Decision Trees. Neural networks have been successfully applied in wide range of supervised and unsupervised learning applications. Neural network methods are not commonly used for data mining tasks, because they often produce incomprehensible models, and require long training times. One way in which the collective properties of a neural network may be used to implement a computational task is by way of the concept of energy minimization. The Hopfield network is well-known example of such an approach. The Hopfield network is useful as content addressable memory or an analog computer for s...
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...
Medical diagnosis using neural network
Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...
Design of fiber optic adaline neural networks
Ghosh, Anjan K.; Trepka, Jim
1997-03-01
Based on possible optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators we describe the design of a single-layer fiber optic Adaline neural network that can be used as a bit pattern classifier. In our design, we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The described new optical neural network design is for optical processing of guided light wave signals, not electronic signals. We analyze the convergence or learning characteristics of the optoelectronic Adaline in the presence of errors in the hardware. We show that with such an optoelectronic Adaline it is possible to detect a desired code word/token/header with good accuracy.
Devices and circuits for nanoelectronic implementation of artificial neural networks
Turel, Ozgur
Biological neural networks perform complicated information processing tasks at speeds better than conventional computers based on conventional algorithms. This has inspired researchers to look into the way these networks function, and propose artificial networks that mimic their behavior. Unfortunately, most artificial neural networks, either software or hardware, do not provide either the speed or the complexity of a human brain. Nanoelectronics, with high density and low power dissipation that it provides, may be used in developing more efficient artificial neural networks. This work consists of two major contributions in this direction. First is the proposal of the CMOL concept, hybrid CMOS-molecular hardware [1-8]. CMOL may circumvent most of the problems in posed by molecular devices, such as low yield, vet provide high active device density, ˜1012/cm 2. The second contribution is CrossNets, artificial neural networks that are based on CMOL. We showed that CrossNets, with their fault tolerance, exceptional speed (˜ 4 to 6 orders of magnitude faster than biological neural networks) can perform any task any artificial neural network can perform. Moreover, there is a hope that if their integration scale is increased to that of human cerebral cortex (˜ 1010 neurons and ˜ 1014 synapses), they may be capable of performing more advanced tasks.
Artificial Neural Network Analysis System
2007-11-02
Contract No. DASG60-00-M-0201 Purchase request no.: Foot in the Door-01 Title Name: Artificial Neural Network Analysis System Company: Atlantic... Artificial Neural Network Analysis System 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) Powell, Bruce C 5d. PROJECT NUMBER 5e. TASK NUMBER...34) 27-02-2001 Report Type N/A Dates Covered (from... to) ("DD MON YYYY") 28-10-2000 27-02-2001 Title and Subtitle Artificial Neural Network Analysis
Architecture Analysis of an FPGA-Based Hopfield Neural Network
Directory of Open Access Journals (Sweden)
Miguel Angelo de Abreu de Sousa
2014-01-01
Full Text Available Interconnections between electronic circuits and neural computation have been a strongly researched topic in the machine learning field in order to approach several practical requirements, including decreasing training and operation times in high performance applications and reducing cost, size, and energy consumption for autonomous or embedded developments. Field programmable gate array (FPGA hardware shows some inherent features typically associated with neural networks, such as, parallel processing, modular executions, and dynamic adaptation, and works on different types of FPGA-based neural networks were presented in recent years. This paper aims to address different aspects of architectural characteristics analysis on a Hopfield Neural Network implemented in FPGA, such as maximum operating frequency and chip-area occupancy according to the network capacity. Also, the FPGA implementation methodology, which does not employ multipliers in the architecture developed for the Hopfield neural model, is presented, in detail.
Hardware demonstration of high-speed networks for satellite applications.
Energy Technology Data Exchange (ETDEWEB)
Donaldson, Jonathon W.; Lee, David S.
2008-09-01
This report documents the implementation results of a hardware demonstration utilizing the Serial RapidIO{trademark} and SpaceWire protocols that was funded by Sandia National Laboratories (SNL's) Laboratory Directed Research and Development (LDRD) office. This demonstration was one of the activities in the Modeling and Design of High-Speed Networks for Satellite Applications LDRD. This effort has demonstrated the transport of application layer packets across both RapidIO and SpaceWire networks to a common downlink destination using small topologies comprised of commercial-off-the-shelf and custom devices. The RapidFET and NEX-SRIO debug and verification tools were instrumental in the successful implementation of the RapidIO hardware demonstration. The SpaceWire hardware demonstration successfully demonstrated the transfer and routing of application data packets between multiple nodes and also was able reprogram remote nodes using configuration bitfiles transmitted over the network, a key feature proposed in node-based architectures (NBAs). Although a much larger network (at least 18 to 27 nodes) would be required to fully verify the design for use in a real-world application, this demonstration has shown that both RapidIO and SpaceWire are capable of routing application packets across a network to a common downlink node, illustrating their potential use in real-world NBAs.
Neural networks and statistical learning
Du, Ke-Lin
2014-01-01
Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
examined, and it appears that considering 'normal' neural network models with, say, 500 samples, the problem of over-fitting is neglible, and therefore it is not taken into consideration afterwards. Numerous model types, often met in control applications, are implemented as neural network models....... - Control concepts including parameter estimation - Control concepts including inverse modelling - Control concepts including optimal control For each of the three groups, different control concepts and specific training methods are detailed described.Further, all control concepts are tested on the same......The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...
Hardware Abstraction and Protocol Optimization for Coded Sensor Networks
DEFF Research Database (Denmark)
Nistor, Maricica; Roetter, Daniel Enrique Lucani; Barros, João
2015-01-01
-efficient protocols that use such an abstraction, as well as mechanisms to optimize a communication protocol in terms of energy consumption. The problem is modeled for different feedback-based techniques, where sensors are connected to a base station, either directly or through relays. We show that for four example......The design of the communication protocols in wireless sensor networks (WSNs) often neglects several key characteristics of the sensor's hardware, while assuming that the number of transmitted bits is the dominating factor behind the system's energy consumption. A closer look at the hardware...... platforms, the use of relays may decrease up to 4.5 times the total energy consumption when the protocol and the hardware are carefully matched. We conclude that: 1) the energy budget for a communication protocol varies significantly on different sensor platforms; and 2) the protocols can be judiciously...
The holographic neural network: Performance comparison with other neural networks
Klepko, Robert
1991-10-01
The artificial neural network shows promise for use in recognition of high resolution radar images of ships. The holographic neural network (HNN) promises a very large data storage capacity and excellent generalization capability, both of which can be achieved with only a few learning trials, unlike most neural networks which require on the order of thousands of learning trials. The HNN is specially designed for pattern association storage, and mathematically realizes the storage and retrieval mechanisms of holograms. The pattern recognition capability of the HNN was studied, and its performance was compared with five other commonly used neural networks: the Adaline, Hamming, bidirectional associative memory, recirculation, and back propagation networks. The patterns used for testing represented artificial high resolution radar images of ships, and appear as a two dimensional topology of peaks with various amplitudes. The performance comparisons showed that the HNN does not perform as well as the other neural networks when using the same test data. However, modification of the data to make it appear more Gaussian distributed, improved the performance of the network. The HNN performs best if the data is completely Gaussian distributed.
VLSI synthesis of digital application specific neural networks
Beagles, Grant; Winters, Kel
1991-01-01
Neural networks tend to fall into two general categories: (1) software simulations, or (2) custom hardware that must be trained. The scope of this project is the merger of these two classifications into a system whereby a software model of a network is trained to perform a specific task and the results used to synthesize a standard cell realization of the network using automated tools.
Neural Network Communications Signal Processing
1994-08-01
Technical Information Report for the Neural Network Communications Signal Processing Program, CDRL A003, 31 March 1993. Software Development Plan for...track changing jamming conditions to provide the decoder with the best log- likelihood ratio metrics at a given time. As part of our development plan we...Artificial Neural Networks (ICANN-91) Volume 2, June 24-28, 1991, pp. 1677-1680. Kohonen, Teuvo, Raivio, Kimmo, Simula, Oli, Venta , 011i, Henriksson
What are artificial neural networks?
DEFF Research Database (Denmark)
Krogh, Anders
2008-01-01
Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...
A Neuron- and a Synapse Chip for Artificial Neural Networks
DEFF Research Database (Denmark)
Lansner, John; Lehmann, Torsten
1992-01-01
A cascadable, analog, CMOS chip set has been developed for hardware implementations of artificial neural networks (ANN's):I) a neuron chip containing an array of neurons with hyperbolic tangent activation functions and adjustable gains, and II) a synapse chip (or a matrix-vector multiplier) where...
Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture
Energy Technology Data Exchange (ETDEWEB)
Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)
2015-01-01
Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.
Complex-Valued Neural Networks
Hirose, Akira
2012-01-01
This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...
Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation.
Maeda, Yutaka; Wakamura, Masatoshi
2005-11-01
Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.
Antenna analysis using neural networks
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
Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.
Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu
2016-07-14
This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.
Efficient implementation of neural network deinterlacing
Seo, Guiwon; Choi, Hyunsoo; Lee, Chulhee
2009-02-01
Interlaced scanning has been widely used in most broadcasting systems. However, there are some undesirable artifacts such as jagged patterns, flickering, and line twitters. Moreover, most recent TV monitors utilize flat panel display technologies such as LCD or PDP monitors and these monitors require progressive formats. Consequently, the conversion of interlaced video into progressive video is required in many applications and a number of deinterlacing methods have been proposed. Recently deinterlacing methods based on neural network have been proposed with good results. On the other hand, with high resolution video contents such as HDTV, the amount of video data to be processed is very large. As a result, the processing time and hardware complexity become an important issue. In this paper, we propose an efficient implementation of neural network deinterlacing using polynomial approximation of the sigmoid function. Experimental results show that these approximations provide equivalent performance with a considerable reduction of complexity. This implementation of neural network deinterlacing can be efficiently incorporated in HW implementation.
Tutorial on neural network applications in high energy physics: A 1992 perspective
Energy Technology Data Exchange (ETDEWEB)
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.
Analysis of EM scattering in Waveguide Filter using Neural Network
Directory of Open Access Journals (Sweden)
Manidipa Nath
2012-03-01
Full Text Available This paper discusses the application of Neural Network (NN technique in the modeling of a typical electromagnetic (EM field scattering problem in a waveguide filter structure [1]. The structure underconsideration is a rectangular waveguide with four dielectric circular rod inserted symmetrically. The Neural Network takes into consideration the geometrical and material parameters of the EM model of the structure and the reflection coefficient values for different frequencies in the frequency band of interest. The Neural Network is trained off line using training data sets generated by the image theory. The work is to find out an acceptable Neural Network model of the waveguide structure having four dielectric post, verification using Method of moment by simulation and the corresponding filter structure practically implemented in hardware for verification.
Stromatias, Evangelos; Neil, Daniel; Pfeiffer, Michael; Galluppi, Francesco; Furber, Steve B; Liu, Shih-Chii
2015-01-01
Increasingly large deep learning architectures, such as Deep Belief Networks (DBNs) are the focus of current machine learning research and achieve state-of-the-art results in different domains. However, both training and execution of large-scale Deep Networks require vast computing resources, leading to high power requirements and communication overheads. The on-going work on design and construction of spike-based hardware platforms offers an alternative for running deep neural networks with significantly lower power consumption, but has to overcome hardware limitations in terms of noise and limited weight precision, as well as noise inherent in the sensor signal. This article investigates how such hardware constraints impact the performance of spiking neural network implementations of DBNs. In particular, the influence of limited bit precision during execution and training, and the impact of silicon mismatch in the synaptic weight parameters of custom hybrid VLSI implementations is studied. Furthermore, the network performance of spiking DBNs is characterized with regard to noise in the spiking input signal. Our results demonstrate that spiking DBNs can tolerate very low levels of hardware bit precision down to almost two bits, and show that their performance can be improved by at least 30% through an adapted training mechanism that takes the bit precision of the target platform into account. Spiking DBNs thus present an important use-case for large-scale hybrid analog-digital or digital neuromorphic platforms such as SpiNNaker, which can execute large but precision-constrained deep networks in real time.
Multigradient for Neural Networks for Equalizers
Directory of Open Access Journals (Sweden)
Chulhee Lee
2003-06-01
Full Text Available Recently, a new training algorithm, multigradient, has been published for neural networks and it is reported that the multigradient outperforms the backpropagation when neural networks are used as a classifier. When neural networks are used as an equalizer in communications, they can be viewed as a classifier. In this paper, we apply the multigradient algorithm to train the neural networks that are used as equalizers. Experiments show that the neural networks trained using the multigradient noticeably outperforms the neural networks trained by the backpropagation.
Communications, Navigation, and Network Reconfigurable Test-bed Flight Hardware Compatibility Test S
2010-01-01
Communications, Navigation, and Network Reconfigurable Test-bed Flight Hardware Compatibility Test Sets and Networks Integration Management Office Testing for the Tracking and Data Relay Satellite System
Analog implementation of pulse-coupled neural networks.
Ota, Y; Wilamowski, B M
1999-01-01
This paper presents a compact architecture for analog CMOS hardware implementation of voltage-mode pulse-coupled neural networks (PCNN's). The hardware implementation methods shows inherent fault tolerance specialties and high speed, which is usually more than an order of magnitude over the software counterpart. A computational style described in this article mimics a biological neural network using pulse-stream signaling and analog summation and multiplication. Pulse-stream encoding technique uses pulse streams to carry information and control analog circuitry, while storing further analog information on the time axis. The main feature of the proposed neuron circuit is that the structure is compact, yet exhibiting all the basic properties of natural biological neurons. Functional and structural forms of neural and synaptic functions are presented along with simulation results. Finally, the proposed design is applied to image processing to demonstrate successful restoration of images and their features.
Relations Between Wavelet Network and Feedforward Neural Network
Institute of Scientific and Technical Information of China (English)
刘志刚; 何正友; 钱清泉
2002-01-01
A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.
HARDWARE IMPLEMENTATION OF SECURE AODV FOR WIRELESS SENSOR NETWORKS
Directory of Open Access Journals (Sweden)
S. Sharmila
2010-12-01
Full Text Available Wireless Sensor Networks are extremely vulnerable to any kind of routing attacks due to several factors such as wireless transmission and resource-constrained nodes. In this respect, securing the packets is of great importance when designing the infrastructure and protocols of sensor networks. This paper describes the hardware architecture of secure routing for wireless sensor networks. The routing path is selected using Ad-hoc on demand distance vector routing protocol (AODV. The data packets are converted into digest using hash functions. The functionality of the proposed method is modeled using Verilog HDL in MODELSIM simulator and the performance is compared with various target devices. The results show that the data packets are secured and defend against the routing attacks with minimum energy consumption.
Neural network chips for trigger purposes in high energy physics
Energy Technology Data Exchange (ETDEWEB)
Gemmeke, H.; Eppler, W.; Fischer, T. [Research Center Karlsruhe (Germany)] [and others
1996-12-31
Two novel neural chips SAND (Simple Applicable Neural Device) and SIOP (Serial Input - Operating Parallel) are described. Both are highly usable for hardware triggers in particle physics. The chips are optimized for a high input data rate at a very low cost basis. The performance of a single SAND chip is 200 MOPS due to four parallel 16 bit multipliers and 40 bit adders working in one clock cycle. The chip is able to implement feedforward neural networks, Kohonen feature maps and radial basis function networks. Four chips will be implemented on a PCI-board for simulation and on a VUE board for trigger and on- and off-line analysis. For small sized feedforward neural networks the bit-serial neuro-chip SIOP may lead to even smaller latencies because each synaptic connection is implemented by its own bit serial multiplier and adder.
Computer, Network, Software, and Hardware Engineering with Applications
Schneidewind, Norman F
2012-01-01
There are many books on computers, networks, and software engineering but none that integrate the three with applications. Integration is important because, increasingly, software dominates the performance, reliability, maintainability, and availability of complex computer and systems. Books on software engineering typically portray software as if it exists in a vacuum with no relationship to the wider system. This is wrong because a system is more than software. It is comprised of people, organizations, processes, hardware, and software. All of these components must be considered in an integr
Plant Growth Models Using Artificial Neural Networks
Bubenheim, David
1997-01-01
In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.
Ocean wave forecasting using recurrent neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Prabaharan, N.
, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off...
Generalization performance of regularized neural network models
DEFF Research Database (Denmark)
Larsen, Jan; Hansen, Lars Kai
1994-01-01
Architecture optimization is a fundamental problem of neural network modeling. The optimal architecture is defined as the one which minimizes the generalization error. This paper addresses estimation of the generalization performance of regularized, complete neural network models. Regularization...
Improved transformer protection using probabilistic neural network ...
African Journals Online (AJOL)
user
This article presents a novel technique to distinguish between magnetizing inrush ... Protective relaying, Probabilistic neural network, Active power relays, Power ... Forward Neural Network (MFFNN) with back-propagation learning technique.
Neural Network for Sparse Reconstruction
Directory of Open Access Journals (Sweden)
Qingfa Li
2014-01-01
Full Text Available We construct a neural network based on smoothing approximation techniques and projected gradient method to solve a kind of sparse reconstruction problems. Neural network can be implemented by circuits and can be seen as an important method for solving optimization problems, especially large scale problems. Smoothing approximation is an efficient technique for solving nonsmooth optimization problems. We combine these two techniques to overcome the difficulties of the choices of the step size in discrete algorithms and the item in the set-valued map of differential inclusion. In theory, the proposed network can converge to the optimal solution set of the given problem. Furthermore, some numerical experiments show the effectiveness of the proposed network in this paper.
The Physics of Neural Networks
Gutfreund, Hanoch; Toulouse, Gerard
The following sections are included: * Introduction * Historical Perspective * Why Statistical Physics? * Purpose and Outline of the Paper * Basic Elements of Neural Network Models * The Biological Neuron * From the Biological to the Formal Neuron * The Formal Neuron * Network Architecture * Network Dynamics * Basic Functions of Neural Network Models * Associative Memory * Learning * Categorization * Generalization * Optimization * The Hopfield Model * Solution of the Model * The Merit of the Hopfield Model * Beyond the Standard Model * The Gardner Approach * A Microcanonical Formulation * The Case of Biased Patterns * A Canonical Formulation * Constraints on the Synaptic Weights * Learning with Errors * Learning with Noise * Hierarchically Correlated Data and Categorization * Hierarchical Data Structures * Storage of Hierarchical Data Structures * Categorization * Generalization * Learning a Classification Task * The Reference Perceptron Problem * The Contiguity Problem * Discussion - Issues of Relevance * The Notion of Attractors and Modes of Computation * The Nature of Attractors * Temporal versus Spatial Coding * Acknowledgements * References
Neural networks and applications tutorial
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.
Meta-Learning Evolutionary Artificial Neural Networks
Abraham, Ajith
2004-01-01
In this paper, we present MLEANN (Meta-Learning Evolutionary Artificial Neural Network), an automatic computational framework for the adaptive optimization of artificial neural networks wherein the neural network architecture, activation function, connection weights; learning algorithm and its parameters are adapted according to the problem. We explored the performance of MLEANN and conventionally designed artificial neural networks for function approximation problems. To evaluate the compara...
Building a Chaotic Proved Neural Network
Bahi, Jacques M; Salomon, Michel
2011-01-01
Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.
FPGA implementation of a pyramidal Weightless Neural Networks learning system.
Al-Alawi, Raida
2003-08-01
A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.
Move Ordering using Neural Networks
Kocsis, L.; Uiterwijk, J.; Van Den Herik, J.
2001-01-01
© Springer-Verlag Berlin Heidelberg 2001. The efficiency of alpha-beta search algorithms heavily depends on the order in which the moves are examined. This paper focuses on using neural networks to estimate the likelihood of a move being the best in a certain position. The moves considered more like
Neural Network based Consumption Forecasting
DEFF Research Database (Denmark)
Madsen, Per Printz
2016-01-01
This paper describe a Neural Network based method for consumption forecasting. This work has been financed by the The ENCOURAGE project. The aims of The ENCOURAGE project is to develop embedded intelligence and integration technologies that will directly optimize energy use in buildings and enable...
Spin glasses and neural networks
Energy Technology Data Exchange (ETDEWEB)
Parga, N. (Comision Nacional de Energia Atomica, San Carlos de Bariloche (Argentina). Centro Atomico Bariloche; Universidad Nacional de Cuyo, San Carlos de Bariloche (Argentina). Inst. Balseiro)
1989-07-01
The mean-field theory of spin glass models has been used as a prototype of systems with frustration and disorder. One of the most interesting related systems are models of associative memories. In these lectures we review the main concepts developed to solve the Sherrington-Kirkpatrick model and its application to neural networks. (orig.).
Artificial neural networks in medicine
Energy Technology Data Exchange (ETDEWEB)
Keller, P.E.
1994-07-01
This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.
Competition Based Neural Networks for Assignment Problems
Institute of Scientific and Technical Information of China (English)
李涛; LuyuanFang
1991-01-01
Competition based neural networks have been used to solve the generalized assignment problem and the quadratic assignment problem.Both problems are very difficult and are ε approximation complete.The neural network approach has yielded highly competitive performance and good performance for the quadratic assignment problem.These neural networks are guaranteed to produce feasible solutions.
Analysis of neural networks through base functions
van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.
Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more
Simplified LQG Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1997-01-01
A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce...
Analysis of Neural Networks through Base Functions
Zwaag, van der B.J.; Slump, C.H.; Spaanenburg, L.
2002-01-01
Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more
Reconfigurable Hardware Architecture for Network Intrusion Detection System
Directory of Open Access Journals (Sweden)
A. Kaleel Rahuman
2012-01-01
Full Text Available Intrusion rule processing in reconfigurable hardware enables intrusion detection and prevention. The use of reconfigurable hardware for network security applications has great strides as Field Programmable Gate Array (FPGA devices have provided larger and faster resources. This proposes architecture called âBV-TCAMâ is presented, which is implemented for an FPGA-based Network Intrusion Detection Systems (NIDS. The BV-TCAM architecture combines the Ternary Content Addressable Memory (TCAM and Bit Vector (BV algorithm to effectively compress the data representation and throughput. A tree bitmap implementation of the BV algorithm is used for source and destination port lookup while a TCAM performs lookup for other header fields, which can be represented as a prefix or exact value. With the aid of small embedded TCAM, packet classification can be implemented in relatively small part of the available logic of an FPGA. The BV-TCAM architecture has been modelled by VHDL. Simulations were performed by MODELSIM. This architecture have to be synthesized and implement our design using Xilinx FPGA device."
Sensitivity of feedforward neural networks to weight errors--
Energy Technology Data Exchange (ETDEWEB)
Stevenson, M.; Widrow, B. (Stanford Univ., CA (USA). Dept. of Engineering-Economic Systems); Winter, R. (U.S. Air Force PSC APO, NY (US))
1990-03-01
An important consideration when implementing neural networks with digital or analog hardware of limited precision is the sensitivity of neural networks to weight errors. In this paper, the authors analyze the sensitivity of feedforward layered networks of Adaline elements (threshold logic units) to weight errors. An approximation is derived which expresses the probability of error for an output neuron of a large network ( a network with many neurons per layer) as a function of the percentage change in the weights. As would be expected, the probability of error increases with the number of layers in the network and with the percentage change in the weights. Surprisingly, the probability of error is essentially independent of the number of weights per neuron and of the number of neurons per layer, as long as these numbers are large (on the order of 100 or more).
A case for spiking neural network simulation based on configurable multiple-FPGA systems.
Yang, Shufan; Wu, Qiang; Li, Renfa
2011-09-01
Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.
Quantum computing in neural networks
Gralewicz, P
2004-01-01
According to the statistical interpretation of quantum theory, quantum computers form a distinguished class of probabilistic machines (PMs) by encoding n qubits in 2n pbits. This raises the possibility of a large-scale quantum computing using PMs, especially with neural networks which have the innate capability for probabilistic information processing. Restricting ourselves to a particular model, we construct and numerically examine the performance of neural circuits implementing universal quantum gates. A discussion on the physiological plausibility of proposed coding scheme is also provided.
Discontinuities in recurrent neural networks.
Gavaldá, R; Siegelmann, H T
1999-04-01
This article studies the computational power of various discontinuous real computational models that are based on the classical analog recurrent neural network (ARNN). This ARNN consists of finite number of neurons; each neuron computes a polynomial net function and a sigmoid-like continuous activation function. We introduce arithmetic networks as ARNN augmented with a few simple discontinuous (e.g., threshold or zero test) neurons. We argue that even with weights restricted to polynomial time computable reals, arithmetic networks are able to compute arbitrarily complex recursive functions. We identify many types of neural networks that are at least as powerful as arithmetic nets, some of which are not in fact discontinuous, but they boost other arithmetic operations in the net function (e.g., neurons that can use divisions and polynomial net functions inside sigmoid-like continuous activation functions). These arithmetic networks are equivalent to the Blum-Shub-Smale model, when the latter is restricted to a bounded number of registers. With respect to implementation on digital computers, we show that arithmetic networks with rational weights can be simulated with exponential precision, but even with polynomial-time computable real weights, arithmetic networks are not subject to any fixed precision bounds. This is in contrast with the ARNN that are known to demand precision that is linear in the computation time. When nontrivial periodic functions (e.g., fractional part, sine, tangent) are added to arithmetic networks, the resulting networks are computationally equivalent to a massively parallel machine. Thus, these highly discontinuous networks can solve the presumably intractable class of PSPACE-complete problems in polynomial time.
Fault Tolerant Neural Network for ECG Signal Classification Systems
Directory of Open Access Journals (Sweden)
MERAH, M.
2011-08-01
Full Text Available The aim of this paper is to apply a new robust hardware Artificial Neural Network (ANN for ECG classification systems. This ANN includes a penalization criterion which makes the performances in terms of robustness. Specifically, in this method, the ANN weights are normalized using the auto-prune method. Simulations performed on the MIT ? BIH ECG signals, have shown that significant robustness improvements are obtained regarding potential hardware artificial neuron failures. Moreover, we show that the proposed design achieves better generalization performances, compared to the standard back-propagation algorithm.
Hardware-software Reconfigurable Techniques for Wireless Sensor Network
Directory of Open Access Journals (Sweden)
C. Rajasekaran
2014-11-01
Full Text Available Now-a-days, the industrial based real time embedded applications are highly developed and they act as a major role in the production cost and real world safety environment. In that, one of the advanced technique is that reconfigurable techniques. This technique plays a major role with wireless sensor networks for the efficient data transmissions. In recent days, most of the industrial applications are works to minimize the size and cost of device. The foremost improvement of the reconfigurable technique is that it circumvents the unnecessary hang and deferral in the device performance. In modern biosphere, Field Programmable Gate Array (FPGA is one of the supreme operative reconfigurable devices and generally used for most of the hardware and software reconfiguration applications. In this study, the exertion pacts with whatever going to make changes in the hardware and software during runtime, it should not disturb the present successively process. This is the main impartial of the study that the changes to be done in an analogous manner at the same time concentrating the cost and power transmission problems during data trans-receiving and also the results to be seen with the help of online manner via the Ethernet cable.
Fuzzy logic systems are equivalent to feedforward neural networks
Institute of Scientific and Technical Information of China (English)
李洪兴
2000-01-01
Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i.e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.
Widrow-cellular neural network and optoelectronic implementation
Bal, Abdullah
A new type of optoelectronic cellular neural network has been developed by providing the capability of coefficients adjusment of cellular neural network (CNN) using Widrow based perceptron learning algorithm. The new supervised cellular neural network is called Widrow-CNN. Despite the unsupervised CNN, the proposed learning algorithm allows to use the Widrow-CNN for various image processing applications easily. Also, the capability of CNN for image processing and feature extraction has been improved using basic joint transform correlation architecture. This hardware application presents high speed processing capability compared to digital applications. The optoelectronic Widrow-CNN has been tested for classic CNN feature extraction problems. It yields the best results even in case of hard feature extraction problems such as diagonal line detection and vertical line determination.
Neural Networks Methodology and Applications
Dreyfus, Gérard
2005-01-01
Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...
Neural Networks for Speech Application.
1987-11-01
operation and neurocrience theories of how neurons process information in the brain. design. Early studies by McCulloch and Pitts dunng the forties led to...developed the commercially available Mark III and Mark IV neurocom- established by McCulloch and Pits. puters that model neural networks and run...ORGANIZERS Infonuiaonienes (1986) FOR Lashley, K. Brain Mehaius and Cblali (129)SPEECHOTECH McCullch. W and Pitts . W, ’A Logical Calculusof the
Analog electronic neural network circuits
Energy Technology Data Exchange (ETDEWEB)
Graf, H.P.; Jackel, L.D. (AT and T Bell Labs., Holmdel, NJ (USA))
1989-07-01
The large interconnectivity and moderate precision required in neural network models present new opportunities for analog computing. This paper discusses analog circuits for a variety of problems such as pattern matching, optimization, and learning. Most of the circuits build so far are relatively small, exploratory designs. The most mature circuits are those for template matching. Chips performing this function are now being applied to pattern recognition problems.
Digital implementation of shunting-inhibitory cellular neural network
Hammadou, Tarik; Bouzerdoum, Abdesselam; Bermak, Amine
2000-05-01
Shunting inhibition is a model of early visual processing which can provide contrast and edge enhancement, and dynamic range compression. An architecture of digital Shunting Inhibitory Cellular Neural Network for real time image processing is presented. The proposed architecture is intended to be used in a complete vision system for edge detection and image enhancement. The present hardware architecture, is modeled and simulated in VHDL. Simulation results show the functional validity of the proposed architecture.
The LILARTI neural network system
Energy Technology Data Exchange (ETDEWEB)
Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.
1992-10-01
The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.
Process Neural Networks Theory and Applications
He, Xingui
2010-01-01
"Process Neural Networks - Theory and Applications" proposes the concept and model of a process neural network for the first time, showing how it expands the mapping relationship between the input and output of traditional neural networks, and enhancing the expression capability for practical problems, with broad applicability to solving problems relating to process in practice. Some theoretical problems such as continuity, functional approximation capability, and computing capability, are strictly proved. The application methods, network construction principles, and optimization alg
Neural network subtyping of depression.
Florio, T M; Parker, G; Austin, M P; Hickie, I; Mitchell, P; Wilhelm, K
1998-10-01
To examine the applicability of a neural network classification strategy to examine the independent contribution of psychomotor disturbance (PMD) and endogeneity symptoms to the DSM-III-R definition of melancholia. We studied 407 depressed patients with the clinical dataset comprising 17 endogeneity symptoms and the 18-item CORE measure of behaviourally rated PMD. A multilayer perception neural network was used to fit non-linear models of varying complexity. A linear discriminant function analysis was also used to generate a model for comparison with the non-linear models. Models (linear and non-linear) using PMD items only and endogeneity symptoms only had similar rates of successful classification, while non-linear models combining both PMD and symptoms scores achieved the best classifications. Our current non-linear model was superior to a linear analysis, a finding which may have wider application to psychiatric classification. Our non-linear analysis of depressive subtypes supports the binary view that melancholic and non-melancholic depression are separate clinical disorders rather than different forms of the same entity. This study illustrates how non-linear modelling with neural networks is a potentially fruitful approach to the study of the diagnostic taxonomy of psychiatric disorders and to clinical decision-making.
Neural networks within multi-core optic fibers.
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-07
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Neural networks within multi-core optic fibers
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-01
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Neural network implementation using bit streams.
Patel, Nitish D; Nguang, Sing Kiong; Coghill, George G
2007-09-01
A new method for the parallel hardware implementation of artificial neural networks (ANNs) using digital techniques is presented. Signals are represented using uniformly weighted single-bit streams. Techniques for generating bit streams from analog or multibit inputs are also presented. This single-bit representation offers significant advantages over multibit representations since they mitigate the fan-in and fan-out issues which are typical to distributed systems. To process these bit streams using ANNs concepts, functional elements which perform summing, scaling, and squashing have been implemented. These elements are modular and have been designed such that they can be easily interconnected. Two new architectures which act as monotonically increasing differentiable nonlinear squashing functions have also been presented. Using these functional elements, a multilayer perceptron (MLP) can be easily constructed. Two examples successfully demonstrate the use of bit streams in the implementation of ANNs. Since every functional element is individually instantiated, the implementation is genuinely parallel. The results clearly show that this bit-stream technique is viable for the hardware implementation of a variety of distributed systems and for ANNs in particular.
Novel quantum inspired binary neural network algorithm
Indian Academy of Sciences (India)
OM PRAKASH PATEL; ARUNA TIWARI
2016-11-01
In this paper, a quantum based binary neural network algorithm is proposed, named as novel quantum binary neural network algorithm (NQ-BNN). It forms a neural network structure by deciding weights and separability parameter in quantum based manner. Quantum computing concept represents solution probabilistically and gives large search space to find optimal value of required parameters using Gaussian random number generator. The neural network structure forms constructively having three number of layers input layer: hidden layer and output layer. A constructive way of deciding the network eliminates the unnecessary training of neural network. A new parameter that is a quantum separability parameter (QSP) is introduced here, which finds an optimal separability plane to classify input samples. During learning, it searches for an optimal separability plane. This parameter is taken as the threshold of neuron for learning of neural network. This algorithm is tested with three benchmark datasets and produces improved results than existing quantum inspired and other classification approaches.
Permitted and forbidden sets in discrete-time linear threshold recurrent neural networks.
Yi, Zhang; Zhang, Lei; Yu, Jiali; Tan, Kok Kiong
2009-06-01
The concepts of permitted and forbidden sets enable a new perspective of the memory in neural networks. Such concepts exhibit interesting dynamics in recurrent neural networks. This paper studies the basic theories of permitted and forbidden sets of the linear threshold discrete-time recurrent neural networks. The linear threshold transfer function has been regarded as an adequate transfer function for recurrent neural networks. Networks with this transfer function form a class of hybrid analog and digital networks which are especially useful for perceptual computations. Networks in discrete time can directly provide algorithms for efficient implementation in digital hardware. The main contribution of this paper is to establish foundations of permitted and forbidden sets. Necessary and sufficient conditions for the linear threshold discrete-time recurrent neural networks are obtained for complete convergence, existence of permitted and forbidden sets, as well as conditionally multiattractivity, respectively. Simulation studies explore some possible interesting practical applications.
Practical neural network recipies in C++
Masters
2014-01-01
This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum
Understanding Neural Networks for Machine Learning using Microsoft Neural Network Algorithm
National Research Council Canada - National Science Library
Nagesh Ramprasad
2016-01-01
.... In this research, focus is on the Microsoft Neural System Algorithm. The Microsoft Neural System Algorithm is a simple implementation of the adaptable and popular neural networks that are used in the machine learning...
OPTIMAL PWM BASED ON REAL—TIME SOLUTION WITH NEURAL NETWORK
Institute of Scientific and Technical Information of China (English)
ShenZhongting; YanYangguang
2002-01-01
A novel concept of neural network based control in pulse-width modulation(PWM)voltage source inverters is presented.On the one hand,the optimal switching an-gles are obtained in real time by the neural network based controller；on the other hand,the output voltage is ad-justed to fit the expected value by neural network when input voltage or loads change.The structure of neural network is simple and easy to be realized by DSP hard-ware system.No large memory used for the existing opti-mal PWM schemes is required in the system.Theoreticalanlysis of the proposed so-called sparse neural network is provided,and the stability of the system is proved.Un-der the control of neural network the error of output volt-age descends sharply,and the system outputs ac voltage with high precision.
Neural network modeling of emotion
Levine, Daniel S.
2007-03-01
This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.
MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION
Directory of Open Access Journals (Sweden)
Artur Popko
2013-06-01
Full Text Available Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.
Narasimhan, Seetharam; Chiel, Hillel J; Bhunia, Swarup
2009-01-01
For implantable neural interface applications, it is important to compress data and analyze spike patterns across multiple channels in real time. Such a computational task for online neural data processing requires an innovative circuit-architecture level design approach for low-power, robust and area-efficient hardware implementation. Conventional microprocessor or Digital Signal Processing (DSP) chips would dissipate too much power and are too large in size for an implantable system. In this paper, we propose a novel hardware design approach, referred to as "Preferential Design" that exploits the nature of the neural signal processing algorithm to achieve a low-voltage, robust and area-efficient implementation using nanoscale process technology. The basic idea is to isolate the critical components with respect to system performance and design them more conservatively compared to the noncritical ones. This allows aggressive voltage scaling for low power operation while ensuring robustness and area efficiency. We have applied the proposed approach to a neural signal processing algorithm using the Discrete Wavelet Transform (DWT) and observed significant improvement in power and robustness over conventional design.
Salience-Affected Neural Networks
Remmelzwaal, Leendert A; Ellis, George F R
2010-01-01
We present a simple neural network model which combines a locally-connected feedforward structure, as is traditionally used to model inter-neuron connectivity, with a layer of undifferentiated connections which model the diffuse projections from the human limbic system to the cortex. This new layer makes it possible to model global effects such as salience, at the same time as the local network processes task-specific or local information. This simple combination network displays interactions between salience and regular processing which correspond to known effects in the developing brain, such as enhanced learning as a result of heightened affect. The cortex biases neuronal responses to affect both learning and memory, through the use of diffuse projections from the limbic system to the cortex. Standard ANNs do not model this non-local flow of information represented by the ascending systems, which are a significant feature of the structure of the brain, and although they do allow associational learning with...
On limited fan-in optimal neural networks
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.; Makaruk, H.E. [Los Alamos National Lab., NM (United States); Draghici, S. [Wayne State Univ., Detroit, MI (United States). Vision and Neural Networks Lab.
1998-03-01
Because VLSI implementations do not cope well with highly interconnected nets the area of a chip growing as the cube of the fan-in--this paper analyses the influence of limited fan in on the size and VLSI optimality of such nets. Two different approaches will show that VLSI- and size-optimal discrete neural networks can be obtained for small (i.e. lower than linear) fan-in values. They have applications to hardware implementations of neural networks. The first approach is based on implementing a certain sub class of Boolean functions, IF{sub n,m} functions. The authors will show that this class of functions can be implemented in VLSI optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan ins. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on neural networks with fan-ins limited to 2. They generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan in values, while relative minimum size solutions can be obtained for fan-ins strictly lower than linear. Finally, a size-optimal neural network having small constant fan-ins will be suggested for IF{sub n,m} functions.
Dynamic Analysis of Structures Using Neural Networks
Directory of Open Access Journals (Sweden)
N. Ahmadi
2008-01-01
Full Text Available In the recent years, neural networks are considered as the best candidate for fast approximation with arbitrary accuracy in the time consuming problems. Dynamic analysis of structures against earthquake has the time consuming process. We employed two kinds of neural networks: Generalized Regression neural network (GR and Back-Propagation Wavenet neural network (BPW, for approximating of dynamic time history response of frame structures. GR is a traditional radial basis function neural network while BPW categorized as a wavelet neural network. In BPW, sigmoid activation functions of hidden layer neurons are substituted with wavelets and weights training are achieved using Scaled Conjugate Gradient (SCG algorithm. Comparison the results of BPW with those of GR in the dynamic analysis of eight story steel frame indicates that accuracy of the properly trained BPW was better than that of GR and therefore, BPW can be efficiently used for approximate dynamic analysis of structures.
Fast Algorithms for Convolutional Neural Networks
Lavin, Andrew; Gray, Scott
2015-01-01
Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We ...
Modelling Microwave Devices Using Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Andrius Katkevičius
2012-04-01
Full Text Available Artificial neural networks (ANN have recently gained attention as fast and flexible equipment for modelling and designing microwave devices. The paper reviews the opportunities to use them for undertaking the tasks on the analysis and synthesis. The article focuses on what tasks might be solved using neural networks, what challenges might rise when using artificial neural networks for carrying out tasks on microwave devices and discusses problem-solving techniques for microwave devices with intermittent characteristics.Article in Lithuanian
Rule Extraction using Artificial Neural Networks
2010-01-01
Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can...
Adaptive optimization and control using neural networks
Energy Technology Data Exchange (ETDEWEB)
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
Forecasting Exchange Rate Using Neural Networks
Raksaseree, Sukhita
2009-01-01
The artificial neural network models become increasingly popular among researchers and investors since many studies have shown that it has superior performance over the traditional statistical model. This paper aims to investigate the neural network performance in forecasting foreign exchange rates based on backpropagation algorithm. The forecast of Thai Baht against seven currencies are conducted to observe the performance of the neural network models using the performance criteria for both ...
Semantic Interpretation of An Artificial Neural Network
1995-12-01
ARTIFICIAL NEURAL NETWORK .7,’ THESIS Stanley Dale Kinderknecht Captain, USAF 770 DEAT7ET77,’H IR O C 7... ARTIFICIAL NEURAL NETWORK THESIS Stanley Dale Kinderknecht Captain, USAF AFIT/GCS/ENG/95D-07 Approved for public release; distribution unlimited The views...Government. AFIT/GCS/ENG/95D-07 SEMANTIC INTERPRETATION OF AN ARTIFICIAL NEURAL NETWORK THESIS Presented to the Faculty of the School of Engineering of
Feature Weight Tuning for Recursive Neural Networks
2014-01-01
This paper addresses how a recursive neural network model can automatically leave out useless information and emphasize important evidence, in other words, to perform "weight tuning" for higher-level representation acquisition. We propose two models, Weighted Neural Network (WNN) and Binary-Expectation Neural Network (BENN), which automatically control how much one specific unit contributes to the higher-level representation. The proposed model can be viewed as incorporating a more powerful c...
IR wireless cluster synapses of HYDRA very large neural networks
Jannson, Tomasz; Forrester, Thomas
2008-04-01
RF/IR wireless (virtual) synapses are critical components of HYDRA (Hyper-Distributed Robotic Autonomy) neural networks, already discussed in two earlier papers. The HYDRA network has the potential to be very large, up to 10 11-neurons and 10 18-synapses, based on already established technologies (cellular RF telephony and IR-wireless LANs). It is organized into almost fully connected IR-wireless clusters. The HYDRA neurons and synapses are very flexible, simple, and low-cost. They can be modified into a broad variety of biologically-inspired brain-like computing capabilities. In this third paper, we focus on neural hardware in general, and on IR-wireless synapses in particular. Such synapses, based on LED/LD-connections, dominate the HYDRA neural cluster.
Fuzzy neural network theory and application
Liu, Puyin
2004-01-01
This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he
Neural networks for nuclear spectroscopy
Energy Technology Data Exchange (ETDEWEB)
Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States)] [and others
1995-12-31
In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.
Neural Networks for Rapid Design and Analysis
Sparks, Dean W., Jr.; Maghami, Peiman G.
1998-01-01
Artificial neural networks have been employed for rapid and efficient dynamics and control analysis of flexible systems. Specifically, feedforward neural networks are designed to approximate nonlinear dynamic components over prescribed input ranges, and are used in simulations as a means to speed up the overall time response analysis process. To capture the recursive nature of dynamic components with artificial neural networks, recurrent networks, which use state feedback with the appropriate number of time delays, as inputs to the networks, are employed. Once properly trained, neural networks can give very good approximations to nonlinear dynamic components, and by their judicious use in simulations, allow the analyst the potential to speed up the analysis process considerably. To illustrate this potential speed up, an existing simulation model of a spacecraft reaction wheel system is executed, first conventionally, and then with an artificial neural network in place.
Sergio Saponara; Tony Bacchillone
2012-01-01
This paper discusses aims, architecture, and security issues of Smart Grid, taking care of the lesson learned at University of Pisa in research projects on smart energy and grid. A key element of Smart Grid is the energy home area network (HAN), for which an implementation is proposed, dealing with its security aspects and showing some solutions for realizing a wireless network based on ZigBee. Possible hardware-software architectures and implementations using COTS (Commercial Off The Shelf) ...
Systolic implementation of neural networks
Energy Technology Data Exchange (ETDEWEB)
De Groot, A.J.; Parker, S.R.
1989-01-01
The backpropagation algorithm for error gradient calculations in multilayer, feed-forward neural networks is derived in matrix form involving inner and outer products. It is demonstrated that these calculations can be carried out efficiently using systolic processing techniques, particularly using the SPRINT, a 64-element systolic processor developed at Lawrence Livermore National Laboratory. This machine contains one million synapses, and forward-propagates 12 million connections per second, using 100 watts of power. When executing the algorithm, each SPRINT processor performs useful work 97% of the time. The theory and applications are confirmed by some nontrivial examples involving seismic signal recognition. 4 refs., 7 figs.
Magnitude Sensitive Competitive Neural Networks
Pelayo Campillos, Enrique; Buldain Pérez, David; Orrite Uruñuela, Carlos
2014-01-01
En esta Tesis se presentan un conjunto de redes neuronales llamadas Magnitude Sensitive Competitive Neural Networks (MSCNNs). Se trata de un conjunto de algoritmos de Competitive Learning que incluyen un término de magnitud como un factor de modulación de la distancia usada en la competición. Al igual que otros métodos competitivos, MSCNNs realizan la cuantización vectorial de los datos, pero el término de magnitud guía el entrenamiento de los centroides de modo que se representan con alto de...
An Analysis of Hardware Requirements for Airborne Tactical Mesh Networking Nodes
2005-03-01
Global PAGES Information Grid, MANET, Wireless, OLSR, Sensor Networks, Tactical 53 Network Topology, Single Board Computer , PC/104, Tern UAV 16. PRICE...21 A . HARDWARE .......................................... 21 1. Single Board Computer ........................ 21 2. Compact Flash...logical choice was to base an improved design on the PC/104 standard for embedded PC architecture. A. HARDWARE 1. Single Board Computer Embedded
Optogenetics in Silicon: A Neural Processor for Predicting Optically Active Neural Networks.
Luo, Junwen; Nikolic, Konstantin; Evans, Benjamin D; Dong, Na; Sun, Xiaohan; Andras, Peter; Yakovlev, Alex; Degenaar, Patrick
2016-08-17
We present a reconfigurable neural processor for real-time simulation and prediction of opto-neural behaviour. We combined a detailed Hodgkin-Huxley CA3 neuron integrated with a four-state Channelrhodopsin-2 (ChR2) model into reconfigurable silicon hardware. Our architecture consists of a Field Programmable Gated Array (FPGA) with a custom-built computing data-path, a separate data management system and a memory approach based router. Advancements over previous work include the incorporation of short and long-term calcium and light-dependent ion channels in reconfigurable hardware. Also, the developed processor is computationally efficient, requiring only 0.03 ms processing time per sub-frame for a single neuron and 9.7 ms for a fully connected network of 500 neurons with a given FPGA frequency of 56.7 MHz. It can therefore be utilized for exploration of closed loop processing and tuning of biologically realistic optogenetic circuitry.
Optogenetics in Silicon: A Neural Processor for Predicting Optically Active Neural Networks.
Junwen Luo; Nikolic, Konstantin; Evans, Benjamin D; Na Dong; Xiaohan Sun; Andras, Peter; Yakovlev, Alex; Degenaar, Patrick
2017-02-01
We present a reconfigurable neural processor for real-time simulation and prediction of opto-neural behaviour. We combined a detailed Hodgkin-Huxley CA3 neuron integrated with a four-state Channelrhodopsin-2 (ChR2) model into reconfigurable silicon hardware. Our architecture consists of a Field Programmable Gated Array (FPGA) with a custom-built computing data-path, a separate data management system and a memory approach based router. Advancements over previous work include the incorporation of short and long-term calcium and light-dependent ion channels in reconfigurable hardware. Also, the developed processor is computationally efficient, requiring only 0.03 ms processing time per sub-frame for a single neuron and 9.7 ms for a fully connected network of 500 neurons with a given FPGA frequency of 56.7 MHz. It can therefore be utilized for exploration of closed loop processing and tuning of biologically realistic optogenetic circuitry.
The Laplacian spectrum of neural networks.
de Lange, Siemon C; de Reus, Marcel A; van den Heuvel, Martijn P
2014-01-13
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these "conventional" graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks.
The Laplacian spectrum of neural networks
de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.
2014-01-01
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286
Neural Network Controlled Visual Saccades
Johnson, Jeffrey D.; Grogan, Timothy A.
1989-03-01
The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.
An overview on development of neural network technology
Lin, Chun-Shin
1993-01-01
The study has been to obtain a bird's-eye view of the current neural network technology and the neural network research activities in NASA. The purpose was two fold. One was to provide a reference document for NASA researchers who want to apply neural network techniques to solve their problems. Another one was to report out survey results regarding NASA research activities and provide a view on what NASA is doing, what potential difficulty exists and what NASA can/should do. In a ten week study period, we interviewed ten neural network researchers in the Langley Research Center and sent out 36 survey forms to researchers at the Johnson Space Center, Lewis Research Center, Ames Research Center and Jet Propulsion Laboratory. We also sent out 60 similar forms to educators and corporation researchers to collect general opinions regarding this field. Twenty-eight survey forms, 11 from NASA researchers and 17 from outside, were returned. Survey results were reported in our final report. In the final report, we first provided an overview on the neural network technology. We reviewed ten neural network structures, discussed the applications in five major areas, and compared the analog, digital and hybrid electronic implementation of neural networks. In the second part, we summarized known NASA neural network research studies and reported the results of the questionnaire survey. Survey results show that most studies are still in the development and feasibility study stage. We compared the techniques, application areas, researchers' opinions on this technology, and many aspects between NASA and non-NASA groups. We also summarized their opinions on difficulties encountered. Applications are considered the top research priority by most researchers. Hardware development and learning algorithm improvement are the next. The lack of financial and management support is among the difficulties in research study. All researchers agree that the use of neural networks could result in
Video Traffic Prediction Using Neural Networks
Directory of Open Access Journals (Sweden)
Miloš Oravec
2008-10-01
Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].
Neural networks with discontinuous/impact activations
Akhmet, Marat
2014-01-01
This book presents as its main subject new models in mathematical neuroscience. A wide range of neural networks models with discontinuities are discussed, including impulsive differential equations, differential equations with piecewise constant arguments, and models of mixed type. These models involve discontinuities, which are natural because huge velocities and short distances are usually observed in devices modeling the networks. A discussion of the models, appropriate for the proposed applications, is also provided. This book also: Explores questions related to the biological underpinning for models of neural networks\\ Considers neural networks modeling using differential equations with impulsive and piecewise constant argument discontinuities Provides all necessary mathematical basics for application to the theory of neural networks Neural Networks with Discontinuous/Impact Activations is an ideal book for researchers and professionals in the field of engineering mathematics that have an interest in app...
Neural Networks for Emotion Classification
Sun, Yafei
2011-01-01
It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. This thesis describes a neural network-based approach for emotion classification. We learn a classifier that can recognize six basic emotions with an average accuracy of 77% over the Cohn-Kanade database. The novelty of this work is that instead of empirically selecting the parameters of the neural network, i.e. the learning rate, activation function parameter, momentum number, the number of nodes in one layer, etc. we developed a strategy that can automatically select comparatively better combination of these parameters. We also introduce another way to perform back propagation. Instead of using the partial differential of the error function, we use optimal algorithm; namely Powell's direction set to minimize the error function. We were also interested in construction an authentic emotion databases. This...
Artificial neural networks in neurosurgery.
Azimi, Parisa; Mohammadi, Hasan Reza; Benzel, Edward C; Shahzadi, Sohrab; Azhari, Shirzad; Montazeri, Ali
2015-03-01
Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery.
Optimizing neural network forecast by immune algorithm
Institute of Scientific and Technical Information of China (English)
YANG Shu-xia; LI Xiang; LI Ning; YANG Shang-dong
2006-01-01
Considering multi-factor influence, a forecasting model was built. The structure of BP neural network was designed, and immune algorithm was applied to optimize its network structure and weight. After training the data of power demand from the year 1980 to 2005 in China, a nonlinear network model was obtained on the relationship between power demand and the factors which had impacts on it, and thus the above proposed method was verified. Meanwhile, the results were compared to those of neural network optimized by genetic algorithm. The results show that this method is superior to neural network optimized by genetic algorithm and is one of the effective ways of time series forecast.
Optimising the topology of complex neural networks
Jiang, Fei; Schoenauer, Marc
2007-01-01
In this paper, we study instances of complex neural networks, i.e. neural netwo rks with complex topologies. We use Self-Organizing Map neural networks whose n eighbourhood relationships are defined by a complex network, to classify handwr itten digits. We show that topology has a small impact on performance and robus tness to neuron failures, at least at long learning times. Performance may howe ver be increased (by almost 10%) by artificial evolution of the network topo logy. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.
A new formulation for feedforward neural networks.
Razavi, Saman; Tolson, Bryan A
2011-10-01
Feedforward neural network is one of the most commonly used function approximation techniques and has been applied to a wide variety of problems arising from various disciplines. However, neural networks are black-box models having multiple challenges/difficulties associated with training and generalization. This paper initially looks into the internal behavior of neural networks and develops a detailed interpretation of the neural network functional geometry. Based on this geometrical interpretation, a new set of variables describing neural networks is proposed as a more effective and geometrically interpretable alternative to the traditional set of network weights and biases. Then, this paper develops a new formulation for neural networks with respect to the newly defined variables; this reformulated neural network (ReNN) is equivalent to the common feedforward neural network but has a less complex error response surface. To demonstrate the learning ability of ReNN, in this paper, two training methods involving a derivative-based (a variation of backpropagation) and a derivative-free optimization algorithms are employed. Moreover, a new measure of regularization on the basis of the developed geometrical interpretation is proposed to evaluate and improve the generalization ability of neural networks. The value of the proposed geometrical interpretation, the ReNN approach, and the new regularization measure are demonstrated across multiple test problems. Results show that ReNN can be trained more effectively and efficiently compared to the common neural networks and the proposed regularization measure is an effective indicator of how a network would perform in terms of generalization.
Drift chamber tracking with neural networks
Energy Technology Data Exchange (ETDEWEB)
Lindsey, C.S.; Denby, B.; Haggerty, H.
1992-10-01
We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.
Coherence resonance in bursting neural networks.
Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J
2015-10-01
Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal-a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.
Neural network classification - A Bayesian interpretation
Wan, Eric A.
1990-01-01
The relationship between minimizing a mean squared error and finding the optimal Bayesian classifier is reviewed. This provides a theoretical interpretation for the process by which neural networks are used in classification. A number of confidence measures are proposed to evaluate the performance of the neural network classifier within a statistical framework.
Adaptive Neurons For Artificial Neural Networks
Tawel, Raoul
1990-01-01
Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.
Isolated Speech Recognition Using Artificial Neural Networks
2007-11-02
In this project Artificial Neural Networks are used as research tool to accomplish Automated Speech Recognition of normal speech. A small size...the first stage of this work are satisfactory and thus the application of artificial neural networks in conjunction with cepstral analysis in isolated word recognition holds promise.
Neural Network Algorithm for Particle Loading
Energy Technology Data Exchange (ETDEWEB)
J. L. V. Lewandowski
2003-04-25
An artificial neural network algorithm for continuous minimization is developed and applied to the case of numerical particle loading. It is shown that higher-order moments of the probability distribution function can be efficiently renormalized using this technique. A general neural network for the renormalization of an arbitrary number of moments is given.
Medical image analysis with artificial neural networks.
Jiang, J; Trundle, P; Ren, J
2010-12-01
Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. Copyright © 2010 Elsevier Ltd. All rights reserved.
Creativity in design and artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Neocleous, C.C.; Esat, I.I. [Brunel Univ. Uxbridge (United Kingdom); Schizas, C.N. [Univ. of Cyprus, Nicosia (Cyprus)
1996-12-31
The creativity phase is identified as an integral part of the design phase. The characteristics of creative persons which are relevant to designing artificial neural networks manifesting aspects of creativity, are identified. Based on these identifications, a general framework of artificial neural network characteristics to implement such a goal are proposed.
Neural Networks for Non-linear Control
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....
Application of Neural Networks for Energy Reconstruction
Damgov, Jordan
2002-01-01
The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.
Neural Networks for Non-linear Control
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....
Introduction to Concepts in Artificial Neural Networks
Niebur, Dagmar
1995-01-01
This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.
Rule Extraction using Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined using pruning algorithm. The ...
International Conference on Artificial Neural Networks (ICANN)
Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics
2015-01-01
The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...
Wavelet Neural Networks for Adaptive Equalization
Institute of Scientific and Technical Information of China (English)
JIANGMinghu; DENGBeixing; GIELENGeorges; ZHANGBo
2003-01-01
A structure based on the Wavelet neural networks (WNNs) is proposed for nonlinear channel equalization in a digital communication system. The construction algorithm of the Minimum error probability (MEP) is presented and applied as a performance criterion to update the parameter matrix of wavelet networks. Our experimental results show that performance of the proposed wavelet networks based on equalizer can significantly improve the neural modeling accuracy, perform quite well in compensating the nonlinear distortion introduced by the channel, and outperform the conventional neural networks in signal to noise ratio and channel non-llnearity.
Evolvable Block-Based Neural Network Design for Applications in Dynamic Environments
Directory of Open Access Journals (Sweden)
Saumil G. Merchant
2010-01-01
Full Text Available Dedicated hardware implementations of artificial neural networks promise to provide faster, lower-power operation when compared to software implementations executing on microprocessors, but rarely do these implementations have the flexibility to adapt and train online under dynamic conditions. A typical design process for artificial neural networks involves offline training using software simulations and synthesis and hardware implementation of the obtained network offline. This paper presents a design of block-based neural networks (BbNNs on FPGAs capable of dynamic adaptation and online training. Specifically the network structure and the internal parameters, the two pieces of the multiparametric evolution of the BbNNs, can be adapted intrinsically, in-field under the control of the training algorithm. This ability enables deployment of the platform in dynamic environments, thereby significantly expanding the range of target applications, deployment lifetimes, and system reliability. The potential and functionality of the platform are demonstrated using several case studies.
Subspace learning of neural networks
Cheng Lv, Jian; Zhou, Jiliu
2010-01-01
PrefaceChapter 1. Introduction1.1 Introduction1.1.1 Linear Neural Networks1.1.2 Subspace Learning1.2 Subspace Learning Algorithms1.2.1 PCA Learning Algorithms1.2.2 MCA Learning Algorithms1.2.3 ICA Learning Algorithms1.3 Methods for Convergence Analysis1.3.1 SDT Method1.3.2 DCT Method1.3.3 DDT Method1.4 Block Algorithms1.5 Simulation Data Set and Notation1.6 ConclusionsChapter 2. PCA Learning Algorithms with Constants Learning Rates2.1 Oja's PCA Learning Algorithms2.1.1 The Algorithms2.1.2 Convergence Issue2.2 Invariant Sets2.2.1 Properties of Invariant Sets2.2.2 Conditions for Invariant Sets2.
Neural networks for damage identification
Energy Technology Data Exchange (ETDEWEB)
Paez, T.L.; Klenke, S.E.
1997-11-01
Efforts to optimize the design of mechanical systems for preestablished use environments and to extend the durations of use cycles establish a need for in-service health monitoring. Numerous studies have proposed measures of structural response for the identification of structural damage, but few have suggested systematic techniques to guide the decision as to whether or not damage has occurred based on real data. Such techniques are necessary because in field applications the environments in which systems operate and the measurements that characterize system behavior are random. This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework; it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.
Nonlinear programming with feedforward neural networks.
Energy Technology Data Exchange (ETDEWEB)
Reifman, J.
1999-06-02
We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf optimization tool.
Learning Processes of Layered Neural Networks
Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.
1995-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network, and a learning equation similar to that of the Boltzmann machine algorithm is obtained. By applying a mean field approximation to the same stochastic feed-forward neural network, a deterministic analog feed-forward network is obtained and the back-propagation learning rule is re-derived.
Learning Algorithms of Multilayer Neural Networks
Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.
1996-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward multilayer neural network, with far interlayer synaptic connections, and we obtain a learning rule similar to that of the Boltzmann machine on the same multilayer structure. By applying a mean field approximation to the stochastic feed-forward neural network, the generalized error back-propagation learning rule is derived for a deterministic analog feed-forward multilayer network with the far interlay...
Research of The Deeper Neural Networks
Directory of Open Access Journals (Sweden)
Xiao You Rong
2016-01-01
Full Text Available Neural networks (NNs have powerful computational abilities and could be used in a variety of applications; however, training these networks is still a difficult problem. With different network structures, many neural models have been constructed. In this report, a deeper neural networks (DNNs architecture is proposed. The training algorithm of deeper neural network insides searching the global optimal point in the actual error surface. Before the training algorithm is designed, the error surface of the deeper neural network is analyzed from simple to complicated, and the features of the error surface is obtained. Based on these characters, the initialization method and training algorithm of DNNs is designed. For the initialization, a block-uniform design method is proposed which separates the error surface into some blocks and finds the optimal block using the uniform design method. For the training algorithm, the improved gradient-descent method is proposed which adds a penalty term into the cost function of the old gradient descent method. This algorithm makes the network have a great approximating ability and keeps the network state stable. All of these improve the practicality of the neural network.
Memristor-based neural networks: Synaptic versus neuronal stochasticity
Naous, Rawan
2016-11-02
In neuromorphic circuits, stochasticity in the cortex can be mapped into the synaptic or neuronal components. The hardware emulation of these stochastic neural networks are currently being extensively studied using resistive memories or memristors. The ionic process involved in the underlying switching behavior of the memristive elements is considered as the main source of stochasticity of its operation. Building on its inherent variability, the memristor is incorporated into abstract models of stochastic neurons and synapses. Two approaches of stochastic neural networks are investigated. Aside from the size and area perspective, the impact on the system performance, in terms of accuracy, recognition rates, and learning, among these two approaches and where the memristor would fall into place are the main comparison points to be considered.
Acute appendicitis diagnosis using artificial neural networks.
Park, Sung Yun; Kim, Sung Min
2015-01-01
Artificial neural networks is one of pattern analyzer method which are rapidly applied on a bio-medical field. The aim of this research was to propose an appendicitis diagnosis system using artificial neural networks (ANNs). Data from 801 patients of the university hospital in Dongguk were used to construct artificial neural networks for diagnosing appendicitis and acute appendicitis. A radial basis function neural network structure (RBF), a multilayer neural network structure (MLNN), and a probabilistic neural network structure (PNN) were used for artificial neural network models. The Alvarado clinical scoring system was used for comparison with the ANNs. The accuracy of the RBF, PNN, MLNN, and Alvarado was 99.80%, 99.41%, 97.84%, and 72.19%, respectively. The area under ROC (receiver operating characteristic) curve of RBF, PNN, MLNN, and Alvarado was 0.998, 0.993, 0.985, and 0.633, respectively. The proposed models using ANNs for diagnosing appendicitis showed good performances, and were significantly better than the Alvarado clinical scoring system (p < 0.001). With cooperation among facilities, the accuracy for diagnosing this serious health condition can be improved.
Mobility Prediction in Wireless Ad Hoc Networks using Neural Networks
Kaaniche, Heni
2010-01-01
Mobility prediction allows estimating the stability of paths in a mobile wireless Ad Hoc networks. Identifying stable paths helps to improve routing by reducing the overhead and the number of connection interruptions. In this paper, we introduce a neural network based method for mobility prediction in Ad Hoc networks. This method consists of a multi-layer and recurrent neural network using back propagation through time algorithm for training.
Neural network regulation driven by autonomous neural firings
Cho, Myoung Won
2016-07-01
Biological neurons naturally fire spontaneously due to the existence of a noisy current. Such autonomous firings may provide a driving force for network formation because synaptic connections can be modified due to neural firings. Here, we study the effect of autonomous firings on network formation. For the temporally asymmetric Hebbian learning, bidirectional connections lose their balance easily and become unidirectional ones. Defining the difference between reciprocal connections as new variables, we could express the learning dynamics as if Ising model spins interact with each other in magnetism. We present a theoretical method to estimate the interaction between the new variables in a neural system. We apply the method to some network systems and find some tendencies of autonomous neural network regulation.
Genetic algorithm for neural networks optimization
Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta
2004-11-01
This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.
Neural networks techniques applied to reservoir engineering
Energy Technology Data Exchange (ETDEWEB)
Flores, M. [Gerencia de Proyectos Geotermoelectricos, Morelia (Mexico); Barragan, C. [RockoHill de Mexico, Indiana (Mexico)
1995-12-31
Neural Networks are considered the greatest technological advance since the transistor. They are expected to be a common household item by the year 2000. An attempt to apply Neural Networks to an important geothermal problem has been made, predictions on the well production and well completion during drilling in a geothermal field. This was done in Los Humeros geothermal field, using two common types of Neural Network models, available in commercial software. Results show the learning capacity of the developed model, and its precision in the predictions that were made.
Assessing Landslide Hazard Using Artificial Neural Network
DEFF Research Database (Denmark)
Farrokhzad, Farzad; Choobbasti, Asskar Janalizadeh; Barari, Amin
2011-01-01
neural network has been developed for use in the stability evaluation of slopes under various geological conditions and engineering requirements. The Artificial neural network model of this research uses slope characteristics as input and leads to the output in form of the probability of failure...... and factor of safety. It can be stated that the trained neural networks are capable of predicting the stability of slopes and safety factor of landslide hazard in study area with an acceptable level of confidence. Landslide hazard analysis and mapping can provide useful information for catastrophic loss...
Estimation of Conditional Quantile using Neural Networks
DEFF Research Database (Denmark)
Kulczycki, P.; Schiøler, Henrik
1999-01-01
The problem of estimating conditional quantiles using neural networks is investigated here. A basic structure is developed using the methodology of kernel estimation, and a theory guaranteeing con-sistency on a mild set of assumptions is provided. The constructed structure constitutes a basis...... for the design of a variety of different neural networks, some of which are considered in detail. The task of estimating conditional quantiles is related to Bayes point estimation whereby a broad range of applications within engineering, economics and management can be suggested. Numerical results illustrating...... the capabilities of the elaborated neural network are also given....
Estimation of Conditional Quantile using Neural Networks
DEFF Research Database (Denmark)
Kulczycki, P.; Schiøler, Henrik
1999-01-01
The problem of estimating conditional quantiles using neural networks is investigated here. A basic structure is developed using the methodology of kernel estimation, and a theory guaranteeing con-sistency on a mild set of assumptions is provided. The constructed structure constitutes a basis...... for the design of a variety of different neural networks, some of which are considered in detail. The task of estimating conditional quantiles is related to Bayes point estimation whereby a broad range of applications within engineering, economics and management can be suggested. Numerical results illustrating...... the capabilities of the elaborated neural network are also given....
Convolutional Neural Network for Image Recognition
Seifnashri, Sahand
2015-01-01
The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.
Review On Applications Of Neural Network To Computer Vision
Li, Wei; Nasrabadi, Nasser M.
1989-03-01
Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.
Threshold control of chaotic neural network.
He, Guoguang; Shrimali, Manish Dev; Aihara, Kazuyuki
2008-01-01
The chaotic neural network constructed with chaotic neurons exhibits rich dynamic behaviour with a nonperiodic associative memory. In the chaotic neural network, however, it is difficult to distinguish the stored patterns in the output patterns because of the chaotic state of the network. In order to apply the nonperiodic associative memory into information search, pattern recognition etc. it is necessary to control chaos in the chaotic neural network. We have studied the chaotic neural network with threshold activated coupling, which provides a controlled network with associative memory dynamics. The network converges to one of its stored patterns or/and reverse patterns which has the smallest Hamming distance from the initial state of the network. The range of the threshold applied to control the neurons in the network depends on the noise level in the initial pattern and decreases with the increase of noise. The chaos control in the chaotic neural network by threshold activated coupling at varying time interval provides controlled output patterns with different temporal periods which depend upon the control parameters.
Nonequilibrium landscape theory of neural networks.
Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin
2013-11-05
The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.
Nonequilibrium landscape theory of neural networks
Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin
2013-01-01
The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape–flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments. PMID:24145451
Character Recognition Using Novel Optoelectronic Neural Network
1993-04-01
17 2.3.7. Learning rule ................................................................... 18 3. ADALINE ... ADALINE neuron and linear separability which provides a justification for multilayer networks. The MADALINE (many ADALINE ) multi layer network is also...element used In many neural networks (Figure 3.1). The ADALINE functions as an adaptive threshold logic element. In digital Implementation, an input
Neural Network for Estimating Conditional Distribution
DEFF Research Database (Denmark)
Schiøler, Henrik; Kulczycki, P.
Neural networks for estimating conditional distributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency is proved from a mild set of assumptions. A number of applications within...... statistcs, decision theory and signal processing are suggested, and a numerical example illustrating the capabilities of the elaborated network is given...
Nonlinear System Control Using Neural Networks
Directory of Open Access Journals (Sweden)
Jaroslava Žilková
2006-10-01
Full Text Available The paper is focused especially on presenting possibilities of applying off-linetrained artificial neural networks at creating the system inverse models that are used atdesigning control algorithm for non-linear dynamic system. The ability of cascadefeedforward neural networks to model arbitrary non-linear functions and their inverses isexploited. This paper presents a quasi-inverse neural model, which works as a speedcontroller of an induction motor. The neural speed controller consists of two cascadefeedforward neural networks subsystems. The first subsystem provides desired statorcurrent components for control algorithm and the second subsystem providescorresponding voltage components for PWM converter. The availability of the proposedcontroller is verified through the MATLAB simulation. The effectiveness of the controller isdemonstrated for different operating conditions of the drive system.
Implementation of pattern recognition algorithm based on RBF neural network
Bouchoux, Sophie; Brost, Vincent; Yang, Fan; Grapin, Jean Claude; Paindavoine, Michel
2002-12-01
In this paper, we present implementations of a pattern recognition algorithm which uses a RBF (Radial Basis Function) neural network. Our aim is to elaborate a quite efficient system which realizes real time faces tracking and identity verification in natural video sequences. Hardware implementations have been realized on an embedded system developed by our laboratory. This system is based on a DSP (Digital Signal Processor) TMS320C6x. The optimization of implementations allow us to obtain a processing speed of 4.8 images (240x320 pixels) per second with a correct rate of 95% of faces tracking and identity verification.
Recognition of Telugu characters using neural networks.
Sukhaswami, M B; Seetharamulu, P; Pujari, A K
1995-09-01
The aim of the present work is to recognize printed and handwritten Telugu characters using artificial neural networks (ANNs). Earlier work on recognition of Telugu characters has been done using conventional pattern recognition techniques. We make an initial attempt here of using neural networks for recognition with the aim of improving upon earlier methods which do not perform effectively in the presence of noise and distortion in the characters. The Hopfield model of neural network working as an associative memory is chosen for recognition purposes initially. Due to limitation in the capacity of the Hopfield neural network, we propose a new scheme named here as the Multiple Neural Network Associative Memory (MNNAM). The limitation in storage capacity has been overcome by combining multiple neural networks which work in parallel. It is also demonstrated that the Hopfield network is suitable for recognizing noisy printed characters as well as handwritten characters written by different "hands" in a variety of styles. Detailed experiments have been carried out using several learning strategies and results are reported. It is shown here that satisfactory recognition is possible using the proposed strategy. A detailed preprocessing scheme of the Telugu characters from digitized documents is also described.
An Introduction to Neural Networks for Hearing Aid Noise Recognition.
Kim, Jun W.; Tyler, Richard S.
1995-01-01
This article introduces the use of multilayered artificial neural networks in hearing aid noise recognition. It reviews basic principles of neural networks, and offers an example of an application in which a neural network is used to identify the presence or absence of noise in speech. The ability of neural networks to "learn" the…
Neural Networks for Dynamic Flight Control
1993-12-01
uses the Adaline (22) model for development of the neural networks. Neural Graphics and other AFIT applications use a slightly different model. The...primary difference in the Nguyen application is that the Adaline uses the nonlinear function .f(a) = tanh(a) where standard backprop uses the sigmoid
Neural networks convergence using physicochemical data.
Karelson, Mati; Dobchev, Dimitar A; Kulshyn, Oleksandr V; Katritzky, Alan R
2006-01-01
An investigation of the neural network convergence and prediction based on three optimization algorithms, namely, Levenberg-Marquardt, conjugate gradient, and delta rule, is described. Several simulated neural networks built using the above three algorithms indicated that the Levenberg-Marquardt optimizer implemented as a back-propagation neural network converged faster than the other two algorithms and provides in most of the cases better prediction. These conclusions are based on eight physicochemical data sets, each with a significant number of compounds comparable to that usually used in the QSAR/QSPR modeling. The superiority of the Levenberg-Marquardt algorithm is revealed in terms of functional dependence of the change of the neural network weights with respect to the gradient of the error propagation as well as distribution of the weight values. The prediction of the models is assessed by the error of the validation sets not used in the training process.
Application of neural networks in coastal engineering
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.
methods. That is why it is becoming popular in various fields including coastal engineering. Waves and tides will play important roles in coastal erosion or accretion. This paper briefly describes the back-propagation neural networks and its application...
Neural Network Based 3D Surface Reconstruction
Directory of Open Access Journals (Sweden)
Vincy Joseph
2009-11-01
Full Text Available This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach
Control of autonomous robot using neural networks
Barton, Adam; Volna, Eva
2017-07-01
The aim of the article is to design a method of control of an autonomous robot using artificial neural networks. The introductory part describes control issues from the perspective of autonomous robot navigation and the current mobile robots controlled by neural networks. The core of the article is the design of the controlling neural network, and generation and filtration of the training set using ART1 (Adaptive Resonance Theory). The outcome of the practical part is an assembled Lego Mindstorms EV3 robot solving the problem of avoiding obstacles in space. To verify models of an autonomous robot behavior, a set of experiments was created as well as evaluation criteria. The speed of each motor was adjusted by the controlling neural network with respect to the situation in which the robot was found.
Additive Feed Forward Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1999-01-01
This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...
TIME SERIES FORECASTING USING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
BOGDAN OANCEA
2013-05-01
Full Text Available Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.
Artificial neural networks a practical course
da Silva, Ivan Nunes; Andrade Flauzino, Rogerio; Liboni, Luisa Helena Bartocci; dos Reis Alves, Silas Franco
2017-01-01
This book provides comprehensive coverage of neural networks, their evolution, their structure, the problems they can solve, and their applications. The first half of the book looks at theoretical investigations on artificial neural networks and addresses the key architectures that are capable of implementation in various application scenarios. The second half is designed specifically for the production of solutions using artificial neural networks to solve practical problems arising from different areas of knowledge. It also describes the various implementation details that were taken into account to achieve the reported results. These aspects contribute to the maturation and improvement of experimental techniques to specify the neural network architecture that is most appropriate for a particular application scope. The book is appropriate for students in graduate and upper undergraduate courses in addition to researchers and professionals.
Additive Feed Forward Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1999-01-01
This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...
A New Stochastic Computing Methodology for Efficient Neural Network Implementation.
Canals, Vincent; Morro, Antoni; Oliver, Antoni; Alomar, Miquel L; Rosselló, Josep L
2016-03-01
This paper presents a new methodology for the hardware implementation of neural networks (NNs) based on probabilistic laws. The proposed encoding scheme circumvents the limitations of classical stochastic computing (based on unipolar or bipolar encoding) extending the representation range to any real number using the ratio of two bipolar-encoded pulsed signals. Furthermore, the novel approach presents practically a total noise-immunity capability due to its specific codification. We introduce different designs for building the fundamental blocks needed to implement NNs. The validity of the present approach is demonstrated through a regression and a pattern recognition task. The low cost of the methodology in terms of hardware, along with its capacity to implement complex mathematical functions (such as the hyperbolic tangent), allows its use for building highly reliable systems and parallel computing.
Artificial neural network and medicine.
Khan, Z H; Mohapatra, S K; Khodiar, P K; Ragu Kumar, S N
1998-07-01
The introduction of human brain functions such as perception and cognition into the computer has been made possible by the use of Artificial Neural Network (ANN). ANN are computer models inspired by the structure and behavior of neurons. Like the brain, ANN can recognize patterns, manage data and most significantly, learn. This learning ability, not seen in other computer models simulating human intelligence, constantly improves its functional accuracy as it keeps on performing. Experience is as important for an ANN as it is for man. It is being increasingly used to supplement and even (may be) replace experts, in medicine. However, there is still scope for improvement in some areas. Its ability to classify and interpret various forms of medical data comes as a helping hand to clinical decision making in both diagnosis and treatment. Treatment planning in medicine, radiotherapy, rehabilitation, etc. is being done using ANN. Morbidity and mortality prediction by ANN in different medical situations can be very helpful for hospital management. ANN has a promising future in fundamental research, medical education and surgical robotics.
Neural network for image segmentation
Skourikhine, Alexei N.; Prasad, Lakshman; Schlei, Bernd R.
2000-10-01
Image analysis is an important requirement of many artificial intelligence systems. Though great effort has been devoted to inventing efficient algorithms for image analysis, there is still much work to be done. It is natural to turn to mammalian vision systems for guidance because they are the best known performers of visual tasks. The pulse- coupled neural network (PCNN) model of the cat visual cortex has proven to have interesting properties for image processing. This article describes the PCNN application to the processing of images of heterogeneous materials; specifically PCNN is applied to image denoising and image segmentation. Our results show that PCNNs do well at segmentation if we perform image smoothing prior to segmentation. We use PCNN for obth smoothing and segmentation. Combining smoothing and segmentation enable us to eliminate PCNN sensitivity to the setting of the various PCNN parameters whose optimal selection can be difficult and can vary even for the same problem. This approach makes image processing based on PCNN more automatic in our application and also results in better segmentation.
Pattern Recognition Using Neural Networks
Directory of Open Access Journals (Sweden)
Santaji Ghorpade
2010-12-01
Full Text Available Face Recognition has been identified as one of the attracting research areas and it has drawn the attention of many researchers due to its varying applications such as security systems, medical systems,entertainment, etc. Face recognition is the preferred mode of identification by humans: it is natural,robust and non-intrusive. A wide variety of systems requires reliable personal recognition schemes to either confirm or determine the identity of an individual requesting their services. The purpose of such schemes is to ensure that the rendered services are accessed only by a legitimate user and no one else.Examples of such applications include secure access to buildings, computer systems, laptops, cellular phones, and ATMs. In the absence of robust personal recognition schemes, these systems are vulnerable to the wiles of an impostor.In this paper we have developed and illustrated a recognition system for human faces using a novel Kohonen self-organizing map (SOM or Self-Organizing Feature Map (SOFM based retrieval system.SOM has good feature extracting property due to its topological ordering. The Facial Analytics results for the 400 images of AT&T database reflects that the face recognition rate using one of the neural network algorithm SOM is 85.5% for 40 persons.
Applications of Pulse-Coupled Neural Networks
Ma, Yide; Wang, Zhaobin
2011-01-01
"Applications of Pulse-Coupled Neural Networks" explores the fields of image processing, including image filtering, image segmentation, image fusion, image coding, image retrieval, and biometric recognition, and the role of pulse-coupled neural networks in these fields. This book is intended for researchers and graduate students in artificial intelligence, pattern recognition, electronic engineering, and computer science. Prof. Yide Ma conducts research on intelligent information processing, biomedical image processing, and embedded system development at the School of Information Sci
NARX neural networks for sequence processing tasks
Hristev, Eugen
2012-01-01
This project aims at researching and implementing a neural network architecture system for the NARX (Nonlinear AutoRegressive with eXogenous inputs) model, used in sequence processing tasks and particularly in time series prediction. The model can fallback to different types of architectures including time-delay neural networks and multi layer perceptron. The NARX simulator tests and compares the different architectures for both synthetic and real data, including the time series o...
Neural network models of protein domain evolution
Sylvia Nagl
2000-01-01
Protein domains are complex adaptive systems, and here a novel procedure is presented that models the evolution of new functional sites within stable domain folds using neural networks. Neural networks, which were originally developed in cognitive science for the modeling of brain functions, can provide a fruitful methodology for the study of complex systems in general. Ethical implications of developing complex systems models of biomolecules are discussed, with particular reference to molecu...
Neural network segmentation of magnetic resonance images
Frederick, Blaise
1990-07-01
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. A neural network classifier for image segmentation was implemented 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. The classifier''s performance was evaluated as a function of network size number of network layers and length of training. A single layer neural network performed quite well at
Logarithmic learning for generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2014-12-01
Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.
Diabetic retinopathy screening using deep neural network.
Ramachandran, Nishanthan; Chiong, Hong Sheng; Sime, Mary Jane; Wilson, Graham A
2017-09-07
Importance There is a burgeoning interest in the use of deep neural network in diabetic retinal screening. To determine whether a deep neural network could satisfactorily detect diabetic retinopathy that requires referral to an ophthalmologist from a local diabetic retinal screening programme and an international database. Design Retrospective audit Samples Diabetic retinal photos from Otago database photographed during October 2016 (485 photos); and 1200 photos from Messidor international database. Receiver operating characteristic curve to illustrate the ability of a deep neural network to identify referable diabetic retinopathy (moderate or worse diabetic retinopathy or exudates within one disc diameter of the fovea). Main Outcome Measures Area under the receiver operating characteristic curve, sensitivity and specificity RESULTS: For detecting referable diabetic retinopathy, the deep neural network had an area under receiver operating characteristic curve of 0.901 (95% CI, 0.807-0.995) with 84.6% sensitivity and 79.7% specificity for Otago and 0.980 (95% CI, 0.973-0.986) with 96.0% sensitivity and 90.0% specificity for Messidor. Conclusions and Relevance This study has shown that a deep neural network can detect referable diabetic retinopathy with sensitivities and specificities close to or better than 80% from both an international and a domestic (New Zealand) database. We believe that deep neural networks can be integrated into community screening once they can successfully detect both diabetic retinopathy and diabetic macular oedema. This article is protected by copyright. All rights reserved.
Neural networks for segmentation, tracking, and identification
Rogers, Steven K.; Ruck, Dennis W.; Priddy, Kevin L.; Tarr, Gregory L.
1992-09-01
The main thrust of this paper is to encourage the use of neural networks to process raw data for subsequent classification. This article addresses neural network techniques for processing raw pixel information. For this paper the definition of neural networks includes the conventional artificial neural networks such as the multilayer perceptrons and also biologically inspired processing techniques. Previously, we have successfully used the biologically inspired Gabor transform to process raw pixel information and segment images. In this paper we extend those ideas to both segment and track objects in multiframe sequences. It is also desirable for the neural network processing data to learn features for subsequent recognition. A common first step for processing raw data is to transform the data and use the transform coefficients as features for recognition. For example, handwritten English characters become linearly separable in the feature space of the low frequency Fourier coefficients. Much of human visual perception can be modelled by assuming low frequency Fourier as the feature space used by the human visual system. The optimum linear transform, with respect to reconstruction, is the Karhunen-Loeve transform (KLT). It has been shown that some neural network architectures can compute approximations to the KLT. The KLT coefficients can be used for recognition as well as for compression. We tested the use of the KLT on the problem of interfacing a nonverbal patient to a computer. The KLT uses an optimal basis set for object reconstruction. For object recognition, the KLT may not be optimal.
A Neural Network for a Class of Extended Linear Variational Inequalities
Institute of Scientific and Technical Information of China (English)
GAO Xingbao
2001-01-01
Linear variational inequality is a uniform approach for some important problems in optimization problems and equilibrium problems. In this paper, a neural network for solving a class of extended linear variational inequality is presented based on the projection method. No parameter is involved in the proposed neural network, its structure is very simple and it can be implemented in simple hardware when the feasible region is simple. The proposed neural network can be used to solve a broad classes of optimization problems and some existing models for solving ordinary linear variational inequalities can be derived from it. The proposed neural network is proved to be Lyapunov stable and converge asymptotically to an exact solution of the problem. The feasibility and effectiveness of the proposed network are confirmed by numerical simulations.
Hopfield neural network based on ant system
Institute of Scientific and Technical Information of China (English)
洪炳镕; 金飞虎; 郭琦
2004-01-01
Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters.This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement.
Neural-Network Object-Recognition Program
Spirkovska, L.; Reid, M. B.
1993-01-01
HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.
A Floating Point Multiplier based FPGA Synthesis for Neural Networks Enhancement
Directory of Open Access Journals (Sweden)
F. BENREKIA,
2010-05-01
Full Text Available FPGA (Field Programmable Gate Array implementation of Artificial Neural Networks (ANNs calls for multipliers of various word lengths. In this paper, a new approach for designing a FloatingPoint Multiplier(FPM is developed and tested using VHDL. With VHDL (Very High Description Language analyzer and logic synthesis software, hardware prototypes could be implemented in FPGA.
Precision requirements for single-layer feed-forward neural networks
Annema, Anne J.; Hoen, K.; Hoen, Klaas; Wallinga, Hans
1994-01-01
This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an
Hidden neural networks: application to speech recognition
DEFF Research Database (Denmark)
Riis, Søren Kamaric
1998-01-01
We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...... (HNNs) with much fewer parameters than conventional HMMs and other hybrids can obtain comparable performance, and for the broad class task it is illustrated how the HNN can be applied as a purely transition based system, where acoustic context dependent transition probabilities are estimated by neural...
Decentralized Control of Dynamic Routing with a Neural Network Algorithm
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
A state-dependent routing algorithm based on the neural network model, which takes advantage of other dynamic routing algorithm for circuit-switched network, is given in [1]. But, the Algorithm in [1] is a centralized control model with complex O (N7), therefore, is difficult to realize by hardware. A simplified algorithm is put forward in this paper, in which routing can be controlled decentralizedly, and its complexity is reduced to O (10N3). Computer simulations are made in a fully connected test network with eight nodes. The results show that the centralized control model has very effective performance that can match RTNR, and the centralized control model is not as good as the centralized one but better than DAR-1.
Matrix representation of a Neural Network
DEFF Research Database (Denmark)
Christensen, Bjørn Klint
This paper describes the implementation of a three-layer feedforward backpropagation neural network. The paper does not explain feedforward, backpropagation or what a neural network is. It is assumed, that the reader knows all this. If not please read chapters 2, 8 and 9 in Parallel Distributed...... Processing, by David Rummelhart (Rummelhart 1986) for an easy-to-read introduction. What the paper does explain is how a matrix representation of a neural net allows for a very simple implementation. The matrix representation is introduced in (Rummelhart 1986, chapter 9), but only for a two-layer linear...... network and the feedforward algorithm. This paper develops the idea further to three-layer non-linear networks and the backpropagation algorithm. Figure 1 shows the layout of a three-layer network. There are I input nodes, J hidden nodes and K output nodes all indexed from 0. Bias-node for the hidden...
Application of Partially Connected Neural Network
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
This paper focuses mainly on application of Partially Connected Backpropagation Neural Network (PCBP) instead of typical Fully Connected Neural Network (FCBP). The initial neural network is fully connected, after training with sample data using cross-entropy as error function, a clustering method is employed to cluster weights between inputs to hidden layer and from hidden to output layer, and connections that are relatively unnecessary are deleted, thus the initial network becomes a PCBP network.Then PCBP can be used in prediction or data mining by training PCBP with data that comes from database. At the end of this paper, several experiments are conducted to illustrate the effects of PCBP using Iris data set.
On neural networks that design neural associative memories.
Chan, H Y; Zak, S H
1997-01-01
The design problem of generalized brain-state-in-a-box (GBSB) type associative memories is formulated as a constrained optimization program, and "designer" neural networks for solving the program in real time are proposed. The stability of the designer networks is analyzed using Barbalat's lemma. The analyzed and synthesized neural associative memories do not require symmetric weight matrices. Two types of the GBSB-based associative memories are analyzed, one when the network trajectories are constrained to reside in the hypercube [-1, 1](n) and the other type when the network trajectories are confined to stay in the hypercube [0, 1](n). Numerical examples and simulations are presented to illustrate the results obtained.
Artificial astrocytes improve neural network performance.
Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-04-19
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.
Stability prediction of berm breakwater using neural network
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Rao, S.; Manjunath, Y.R.
. In order to allow the network to learn both non-linear and linear relationships between input nodes and output nodes, multiple-layer networks are often used. Among many neural network architectures, the three layers feed forward backpropagation neural...
Pattern Classification using Simplified Neural Networks
Kamruzzaman, S M
2010-01-01
In recent years, many neural network models have been proposed for pattern classification, function approximation and regression problems. This paper presents an approach for classifying patterns from simplified NNs. Although the predictive accuracy of ANNs is often higher than that of other methods or human experts, it is often said that ANNs are practically "black boxes", due to the complexity of the networks. In this paper, we have an attempted to open up these black boxes by reducing the complexity of the network. The factor makes this possible is the pruning algorithm. By eliminating redundant weights, redundant input and hidden units are identified and removed from the network. Using the pruning algorithm, we have been able to prune networks such that only a few input units, hidden units and connections left yield a simplified network. Experimental results on several benchmarks problems in neural networks show the effectiveness of the proposed approach with good generalization ability.
Wireless multimedia sensor networks on reconfigurable hardware information reduction techniques
Ang, Li-minn; Chew, Li Wern; Yeong, Lee Seng; Chia, Wai Chong
2013-01-01
Traditional wireless sensor networks (WSNs) capture scalar data such as temperature, vibration, pressure, or humidity. Motivated by the success of WSNs and also with the emergence of new technology in the form of low-cost image sensors, researchers have proposed combining image and audio sensors with WSNs to form wireless multimedia sensor networks (WMSNs).
Modelling Spiking Neural Network from the Architecture Evaluation Perspective
Institute of Scientific and Technical Information of China (English)
Yu Ji; You-Hui Zhang; Wei-Min Zheng
2016-01-01
The brain-inspired spiking neural network (SNN) computing paradigm offers the potential for low-power and scalable computing, suited to many intelligent tasks that conventional computational systems find diﬃcult. On the other hand, NoC (network-on-chips) based very large scale integration (VLSI) systems have been widely used to mimic neuro-biological architectures (including SNNs). This paper proposes an evaluation methodology for SNN applications from the aspect of micro-architecture. First, we extract accurate SNN models from existing simulators of neural systems. Second, a cycle-accurate NoC simulator is implemented to execute the aforementioned SNN applications to get timing and energy-consumption information. We believe this method not only benefits the exploration of NoC design space but also bridges the gap between applications (especially those from the neuroscientists’ community) and neuromorphic hardware. Based on the method, we have evaluated some typical SNNs in terms of timing and energy. The method is valuable for the development of neuromorphic hardware and applications.
Artificial neural network intelligent method for prediction
Trifonov, Roumen; Yoshinov, Radoslav; Pavlova, Galya; Tsochev, Georgi
2017-09-01
Accounting and financial classification and prediction problems are high challenge and researchers use different methods to solve them. Methods and instruments for short time prediction of financial operations using artificial neural network are considered. The methods, used for prediction of financial data as well as the developed forecasting system with neural network are described in the paper. The architecture of a neural network used four different technical indicators, which are based on the raw data and the current day of the week is presented. The network developed is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.
Directory of Open Access Journals (Sweden)
Sergio Saponara
2012-01-01
Full Text Available This paper discusses aims, architecture, and security issues of Smart Grid, taking care of the lesson learned at University of Pisa in research projects on smart energy and grid. A key element of Smart Grid is the energy home area network (HAN, for which an implementation is proposed, dealing with its security aspects and showing some solutions for realizing a wireless network based on ZigBee. Possible hardware-software architectures and implementations using COTS (Commercial Off The Shelf components are presented for key building blocks of the energy HAN such as smart power meters and plugs and a home smart information box providing energy management policy and supporting user's energy awareness.
Artificial Neural Networks and Instructional Technology.
Carlson, Patricia A.
1991-01-01
Artificial neural networks (ANN), part of artificial intelligence, are discussed. Such networks are fed sample cases (training sets), learn how to recognize patterns in the sample data, and use this experience in handling new cases. Two cognitive roles for ANNs (intelligent filters and spreading, associative memories) are examined. Prototypes…
Learning drifting concepts with neural networks
Biehl, Michael; Schwarze, Holm
1993-01-01
The learning of time-dependent concepts with a neural network is studied analytically and numerically. The linearly separable target rule is represented by an N-vector, whose time dependence is modelled by a random or deterministic drift process. A single-layer network is trained online using differ
Estimating Conditional Distributions by Neural Networks
DEFF Research Database (Denmark)
Kulczycki, P.; Schiøler, Henrik
1998-01-01
Neural Networks for estimating conditionaldistributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency property is considered from a mild set of assumptions. A number of applications...
Artificial Neural Networks and Instructional Technology.
Carlson, Patricia A.
1991-01-01
Artificial neural networks (ANN), part of artificial intelligence, are discussed. Such networks are fed sample cases (training sets), learn how to recognize patterns in the sample data, and use this experience in handling new cases. Two cognitive roles for ANNs (intelligent filters and spreading, associative memories) are examined. Prototypes…
Neural networks as perpetual information generators
Englisch, Harald; Xiao, Yegao; Yao, Kailun
1991-07-01
The information gain in a neural network cannot be larger than the bit capacity of the synapses. It is shown that the equation derived by Engel et al. [Phys. Rev. A 42, 4998 (1990)] for the strongly diluted network with persistent stimuli contradicts this condition. Furthermore, for any time step the correct equation is derived by taking the correlation between random variables into account.
A quantum-implementable neural network model
Chen, Jialin; Wang, Lingli; Charbon, Edoardo
2017-10-01
A quantum-implementable neural network, namely quantum probability neural network (QPNN) model, is proposed in this paper. QPNN can use quantum parallelism to trace all possible network states to improve the result. Due to its unique quantum nature, this model is robust to several quantum noises under certain conditions, which can be efficiently implemented by the qubus quantum computer. Another advantage is that QPNN can be used as memory to retrieve the most relevant data and even to generate new data. The MATLAB experimental results of Iris data classification and MNIST handwriting recognition show that much less neuron resources are required in QPNN to obtain a good result than the classical feedforward neural network. The proposed QPNN model indicates that quantum effects are useful for real-life classification tasks.
Neural Network Approaches to Visual Motion Perception
Institute of Scientific and Technical Information of China (English)
郭爱克; 杨先一
1994-01-01
This paper concerns certain difficult problems in image processing and perception: neuro-computation of visual motion information. The first part of this paper deals with the spatial physiological integration by the figure-ground discrimination neural network in the visual system of the fly. We have outlined the fundamental organization and algorithms of this neural network, and mainly concentrated on the results of computer simulations of spatial physiological integration. It has been shown that the gain control mechanism , the nonlinearity of synaptic transmission characteristic , the interaction between the two eyes , and the directional selectivity of the pool cells play decisive roles in the spatial physiological integration. In the second part, we have presented a self-organizing neural network for the perception of visual motion by using a retinotopic array of Reichardt’s motion detectors and Kohonen’s self-organizing maps. It .has been demonstrated by computer simulations that the network is abl
Improving neural network performance on SIMD architectures
Limonova, Elena; Ilin, Dmitry; Nikolaev, Dmitry
2015-12-01
Neural network calculations for the image recognition problems can be very time consuming. In this paper we propose three methods of increasing neural network performance on SIMD architectures. The usage of SIMD extensions is a way to speed up neural network processing available for a number of modern CPUs. In our experiments, we use ARM NEON as SIMD architecture example. The first method deals with half float data type for matrix computations. The second method describes fixed-point data type for the same purpose. The third method considers vectorized activation functions implementation. For each method we set up a series of experiments for convolutional and fully connected networks designed for image recognition task.
Stability analysis of discrete-time BAM neural networks based on standard neural network models
Institute of Scientific and Technical Information of China (English)
ZHANG Sen-lin; LIU Mei-qin
2005-01-01
To facilitate stability analysis of discrete-time bidirectional associative memory (BAM) neural networks, they were converted into novel neural network models, termed standard neural network models (SNNMs), which interconnect linear dynamic systems and bounded static nonlinear operators. By combining a number of different Lyapunov functionals with S-procedure, some useful criteria of global asymptotic stability and global exponential stability of the equilibrium points of SNNMs were derived. These stability conditions were formulated as linear matrix inequalities (LMIs). So global stability of the discrete-time BAM neural networks could be analyzed by using the stability results of the SNNMs. Compared to the existing stability analysis methods, the proposed approach is easy to implement, less conservative, and is applicable to other recurrent neural networks.
Neural-networks-based Modelling and a Fuzzy Neural Networks Controller of MCFC
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
Molten Carbonate Fuel Cells (MCFC) are produced with a highly efficient and clean power generation technology which will soon be widely utilized. The temperature characters of MCFC stack are briefly analyzed. A radial basis function (RBF) neural networks identification technology is applied to set up the temperature nonlinear model of MCFC stack, and the identification structure, algorithm and modeling training process are given in detail. A fuzzy controller of MCFC stack is designed. In order to improve its online control ability, a neural network trained by the I/O data of a fuzzy controller is designed. The neural networks can memorize and expand the inference rules of the fuzzy controller and substitute for the fuzzy controller to control MCFC stack online. A detailed design of the controller is given. The validity of MCFC stack modelling based on neural networks and the superior performance of the fuzzy neural networks controller are proved by Simulations.
Neural Network Based Montioring and Control of Fluidized Bed.
Energy Technology Data Exchange (ETDEWEB)
Bodruzzaman, M.; Essawy, M.A.
1996-04-01
The goal of this project was to develop chaos analysis and neural network-based modeling techniques and apply them to the pressure-drop data obtained from the Fluid Bed Combustion (FBC) system (a small scale prototype model) located at the Federal Energy Technology Center (FETC)-Morgantown. The second goal was to develop neural network-based chaos control techniques and provide a suggestive prototype for possible real-time application to the FBC system. The experimental pressure data were collected from a cold FBC experimental set-up at the Morgantown Center. We have performed several analysis on these data in order to unveil their dynamical and chaotic characteristics. The phase-space attractors were constructed from the one dimensional time series data, using the time-delay embedding method, for both normal and abnormal conditions. Several identifying parameters were also computed from these attractors such as the correlation dimension, the Kolmogorov entropy, and the Lyapunov exponents. These chaotic attractor parameters can be used to discriminate between the normal and abnormal operating conditions of the FBC system. It was found that, the abnormal data has higher correlation dimension, larger Kolmogorov entropy and larger positive Lyapunov exponents as compared to the normal data. Chaotic system control using neural network based techniques were also investigated and compared to conventional chaotic system control techniques. Both types of chaotic system control techniques were applied to some typical chaotic systems such as the logistic, the Henon, and the Lorenz systems. A prototype model for real-time implementation of these techniques has been suggested to control the FBC system. These models can be implemented for real-time control in a next phase of the project after obtaining further measurements from the experimental model. After testing the control algorithms developed for the FBC model, the next step is to implement them on hardware and link them to
Open hardware: a role to play in wireless sensor networks?
Fisher, Roy; Ledwaba, Lehlogonolo; Hancke, Gerhard; Kruger, Carel
2015-03-20
The concept of the Internet of Things is rapidly becoming a reality, with many applications being deployed within industrial and consumer sectors. At the 'thing' level-devices and inter-device network communication-the core technical building blocks are generally the same as those found in wireless sensor network implementations. For the Internet of Things to continue growing, we need more plentiful resources for building intelligent devices and sensor networks. Unfortunately, current commercial devices, e.g., sensor nodes and network gateways, tend to be expensive and proprietary, which presents a barrier to entry and arguably slows down further development. There are, however, an increasing number of open embedded platforms available and also a wide selection of off-the-shelf components that can quickly and easily be built into device and network gateway solutions. The question is whether these solutions measure up to built-for-purpose devices. In the paper, we provide a comparison of existing built-for-purpose devices against open source devices. For comparison, we have also designed and rapidly prototyped a sensor node based on off-the-shelf components. We show that these devices compare favorably to built-for-purpose devices in terms of performance, power and cost. Using open platforms and off-the-shelf components would allow more developers to build intelligent devices and sensor networks, which could result in a better overall development ecosystem, lower barriers to entry and rapid growth in the number of IoT applications.
Dynamic pricing by hopfield neural network
Institute of Scientific and Technical Information of China (English)
Lusajo M Minga; FENG Yu-qiang(冯玉强); LI Yi-jun(李一军); LU Yang(路杨); Kimutai Kimeli
2004-01-01
The increase in the number of shopbots users in e-commerce has triggered flexibility of sellers in their pricing strategies. Sellers see the importance of automated price setting which provides efficient services to a large number of buyers who are using shopbots. This paper studies the characteristic of decreasing energy with time in a continuous model of a Hopfield neural network that is the decreasing of errors in the network with respect to time. The characteristic shows that it is possible to use Hopfield neural network to get the main factor of dynamic pricing; the least variable cost, from production function principles. The least variable cost is obtained by reducing or increasing the input combination factors, and then making the comparison of the network output with the desired output, where the difference between the network output and desired output will be decreasing in the same manner as in the Hopfield neural network energy. Hopfield neural network will simplify the rapid change of prices in e-commerce during transaction that depends on the demand quantity for demand sensitive model of pricing.
Neutron spectrometry with artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Rodriguez, J.M.; Mercado S, G.A. [Universidad Autonoma de Zacatecas, A.P. 336, 98000 Zacatecas (Mexico); Iniguez de la Torre Bayo, M.P. [Universidad de Valladolid, Valladolid (Spain); Barquero, R. [Hospital Universitario Rio Hortega, Valladolid (Spain); Arteaga A, T. [Envases de Zacatecas, S.A. de C.V., Zacatecas (Mexico)]. e-mail: rvega@cantera.reduaz.mx
2005-07-01
An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using 129 neutron spectra. These include isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra from mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-bin ned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and the respective spectrum was used as output during neural network training. After training the network was tested with the Bonner spheres count rates produced by a set of neutron spectra. This set contains data used during network training as well as data not used. Training and testing was carried out in the Mat lab program. To verify the network unfolding performance the original and unfolded spectra were compared using the {chi}{sup 2}-test and the total fluence ratios. The use of Artificial Neural Networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)
Neural network technologies for image classification
Korikov, A. M.; Tungusova, A. V.
2015-11-01
We analyze the classes of problems with an objective necessity to use neural network technologies, i.e. representation and resolution problems in the neural network logical basis. Among these problems, image recognition takes an important place, in particular the classification of multi-dimensional data based on information about textural characteristics. These problems occur in aerospace and seismic monitoring, materials science, medicine and other. We reviewed different approaches for the texture description: statistical, structural, and spectral. We developed a neural network technology for resolving a practical problem of cloud image classification for satellite snapshots from the spectroradiometer MODIS. The cloud texture is described by the statistical characteristics of the GLCM (Gray Level Co- Occurrence Matrix) method. From the range of neural network models that might be applied for image classification, we chose the probabilistic neural network model (PNN) and developed an implementation which performs the classification of the main types and subtypes of clouds. Also, we chose experimentally the optimal architecture and parameters for the PNN model which is used for image classification.
Representations in neural network based empirical potentials
Cubuk, Ekin D.; Malone, Brad D.; Onat, Berk; Waterland, Amos; Kaxiras, Efthimios
2017-07-01
Many structural and mechanical properties of crystals, glasses, and biological macromolecules can be modeled from the local interactions between atoms. These interactions ultimately derive from the quantum nature of electrons, which can be prohibitively expensive to simulate. Machine learning has the potential to revolutionize materials modeling due to its ability to efficiently approximate complex functions. For example, neural networks can be trained to reproduce results of density functional theory calculations at a much lower cost. However, how neural networks reach their predictions is not well understood, which has led to them being used as a "black box" tool. This lack of understanding is not desirable especially for applications of neural networks in scientific inquiry. We argue that machine learning models trained on physical systems can be used as more than just approximations since they had to "learn" physical concepts in order to reproduce the labels they were trained on. We use dimensionality reduction techniques to study in detail the representation of silicon atoms at different stages in a neural network, which provides insight into how a neural network learns to model atomic interactions.
Using neural networks to describe tracer correlations
Directory of Open Access Journals (Sweden)
D. J. Lary
2004-01-01
Full Text Available Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and methane volume mixing ratio (v.m.r.. In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE which has continuously observed CH4 (but not N2O from 1991 till the present. The neural network Fortran code used is available for download.
Estimates on compressed neural networks regression.
Zhang, Yongquan; Li, Youmei; Sun, Jianyong; Ji, Jiabing
2015-03-01
When the neural element number n of neural networks is larger than the sample size m, the overfitting problem arises since there are more parameters than actual data (more variable than constraints). In order to overcome the overfitting problem, we propose to reduce the number of neural elements by using compressed projection A which does not need to satisfy the condition of Restricted Isometric Property (RIP). By applying probability inequalities and approximation properties of the feedforward neural networks (FNNs), we prove that solving the FNNs regression learning algorithm in the compressed domain instead of the original domain reduces the sample error at the price of an increased (but controlled) approximation error, where the covering number theory is used to estimate the excess error, and an upper bound of the excess error is given.
Community structure of complex networks based on continuous neural network
Dai, Ting-ting; Shan, Chang-ji; Dong, Yan-shou
2017-09-01
As a new subject, the research of complex networks has attracted the attention of researchers from different disciplines. Community structure is one of the key structures of complex networks, so it is a very important task to analyze the community structure of complex networks accurately. In this paper, we study the problem of extracting the community structure of complex networks, and propose a continuous neural network (CNN) algorithm. It is proved that for any given initial value, the continuous neural network algorithm converges to the eigenvector of the maximum eigenvalue of the network modularity matrix. Therefore, according to the stability of the evolution of the network symbol will be able to get two community structure.
Identification and Position Control of Marine Helm using Artificial Neural Network Neural Network
Directory of Open Access Journals (Sweden)
Hui ZHU
2008-02-01
Full Text Available If nonlinearities such as saturation of the amplifier gain and motor torque, gear backlash, and shaft compliances- just to name a few - are considered in the position control system of marine helm, traditional control methods are no longer sufficient to be used to improve the performance of the system. In this paper an alternative approach to traditional control methods - a neural network reference controller - is proposed to establish an adaptive control of the position of the marine helm to achieve the controlled variable at the command position. This neural network controller comprises of two neural networks. One is the plant model network used to identify the nonlinear system and the other the controller network used to control the output to follow the reference model. The experimental results demonstrate that this adaptive neural network reference controller has much better control performance than is obtained with traditional controllers.
An efficient automated parameter tuning framework for spiking neural networks.
Carlson, Kristofor D; Nageswaran, Jayram Moorkanikara; Dutt, Nikil; Krichmar, Jeffrey L
2014-01-01
As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural plasticity, vision systems, auditory systems, neural oscillations, and many other important topics of neural function. Additionally, SNNs are particularly well-adapted to run on neuromorphic hardware that will support biological brain-scale architectures. Although the inclusion of realistic plasticity equations, neural dynamics, and recurrent topologies has increased the descriptive power of SNNs, it has also made the task of tuning these biologically realistic SNNs difficult. To meet this challenge, we present an automated parameter tuning framework capable of tuning SNNs quickly and efficiently using evolutionary algorithms (EA) and inexpensive, readily accessible graphics processing units (GPUs). A sample SNN with 4104 neurons was tuned to give V1 simple cell-like tuning curve responses and produce self-organizing receptive fields (SORFs) when presented with a random sequence of counterphase sinusoidal grating stimuli. A performance analysis comparing the GPU-accelerated implementation to a single-threaded central processing unit (CPU) implementation was carried out and showed a speedup of 65× of the GPU implementation over the CPU implementation, or 0.35 h per generation for GPU vs. 23.5 h per generation for CPU. Additionally, the parameter value solutions found in the tuned SNN were studied and found to be stable and repeatable. The automated parameter tuning framework presented here will be of use to both the computational neuroscience and neuromorphic engineering communities, making the process of constructing and tuning large-scale SNNs much quicker and easier.
Digital systems for artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Atlas, L.E. (Interactive Systems Design Lab., Univ. of Washington, WA (US)); Suzuki, Y. (NTT Human Interface Labs. (US))
1989-11-01
A tremendous flurry of research activity has developed around artificial neural systems. These systems have also been tested in many applications, often with positive results. Most of this work has taken place as digital simulations on general-purpose serial or parallel digital computers. Specialized neural network emulation systems have also been developed for more efficient learning and use. The authors discussed how dedicated digital VLSI integrated circuits offer the highest near-term future potential for this technology.
Open Hardware: A Role to Play in Wireless Sensor Networks?
Directory of Open Access Journals (Sweden)
Roy Fisher
2015-03-01
Full Text Available The concept of the Internet of Things is rapidly becoming a reality, with many applications being deployed within industrial and consumer sectors. At the ‘thing’ level—devices and inter-device network communication—the core technical building blocks are generally the same as those found in wireless sensor network implementations. For the Internet of Things to continue growing, we need more plentiful resources for building intelligent devices and sensor networks. Unfortunately, current commercial devices, e.g., sensor nodes and network gateways, tend to be expensive and proprietary, which presents a barrier to entry and arguably slows down further development. There are, however, an increasing number of open embedded platforms available and also a wide selection of off-the-shelf components that can quickly and easily be built into device and network gateway solutions. The question is whether these solutions measure up to built-for-purpose devices. In the paper, we provide a comparison of existing built-for-purpose devices against open source devices. For comparison, we have also designed and rapidly prototyped a sensor node based on off-the-shelf components. We show that these devices compare favorably to built-for-purpose devices in terms of performance, power and cost. Using open platforms and off-the-shelf components would allow more developers to build intelligent devices and sensor networks, which could result in a better overall development ecosystem, lower barriers to entry and rapid growth in the number of IoT applications.
Equivalence of Conventional and Modified Network of Generalized Neural Elements
Directory of Open Access Journals (Sweden)
E. V. Konovalov
2016-01-01
Full Text Available The article is devoted to the analysis of neural networks consisting of generalized neural elements. The first part of the article proposes a new neural network model — a modified network of generalized neural elements (MGNE-network. This network developes the model of generalized neural element, whose formal description contains some flaws. In the model of the MGNE-network these drawbacks are overcome. A neural network is introduced all at once, without preliminary description of the model of a single neural element and method of such elements interaction. The description of neural network mathematical model is simplified and makes it relatively easy to construct on its basis a simulation model to conduct numerical experiments. The model of the MGNE-network is universal, uniting properties of networks consisting of neurons-oscillators and neurons-detectors. In the second part of the article we prove the equivalence of the dynamics of the two considered neural networks: the network, consisting of classical generalized neural elements, and MGNE-network. We introduce the definition of equivalence in the functioning of the generalized neural element and the MGNE-network consisting of a single element. Then we introduce the definition of the equivalence of the dynamics of the two neural networks in general. It is determined the correlation of different parameters of the two considered neural network models. We discuss the issue of matching the initial conditions of the two considered neural network models. We prove the theorem about the equivalence of the dynamics of the two considered neural networks. This theorem allows us to apply all previously obtained results for the networks, consisting of classical generalized neural elements, to the MGNE-network.
Implementing Signature Neural Networks with Spiking Neurons.
Carrillo-Medina, José Luis; Latorre, Roberto
2016-01-01
Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm-i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data-to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence
Implementing Signature Neural Networks with Spiking Neurons
Carrillo-Medina, José Luis; Latorre, Roberto
2016-01-01
Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm—i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data—to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the
Network Traffic Prediction based on Particle Swarm BP Neural Network
Directory of Open Access Journals (Sweden)
Yan Zhu
2013-11-01
Full Text Available The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and particle swarm optimization algorithm is proposed to optimize the weight and threshold value of BP neural network. After network traffic prediction experiment, we can conclude that optimized BP network traffic prediction based on PSO-ABC has high prediction accuracy and has stable prediction performance.
Training Deep Spiking Neural Networks Using Backpropagation.
Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael
2016-01-01
Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.
Foreign currency rate forecasting using neural networks
Pandya, Abhijit S.; Kondo, Tadashi; Talati, Amit; Jayadevappa, Suryaprasad
2000-03-01
Neural networks are increasingly being used as a forecasting tool in many forecasting problems. This paper discusses the application of neural networks in predicting daily foreign exchange rates between the USD, GBP as well as DEM. We approach the problem from a time-series analysis framework - where future exchange rates are forecasted solely using past exchange rates. This relies on the belief that the past prices and future prices are very close related, and interdependent. We present the result of training a neural network with historical USD-GBP data. The methodology used in explained, as well as the training process. We discuss the selection of inputs to the network, and present a comparison of using the actual exchange rates and the exchange rate differences as inputs. Price and rate differences are the preferred way of training neural network in financial applications. Results of both approaches are present together for comparison. We show that the network is able to learn the trends in the exchange rate movements correctly, and present the results of the prediction over several periods of time.
Training Deep Spiking Neural Networks using Backpropagation
Directory of Open Access Journals (Sweden)
Jun Haeng Lee
2016-11-01
Full Text Available Deep spiking neural networks (SNNs hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.
Kannada character recognition system using neural network
Kumar, Suresh D. S.; Kamalapuram, Srinivasa K.; Kumar, Ajay B. R.
2013-03-01
Handwriting recognition has been one of the active and challenging research areas in the field of pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. As there is no sufficient number of works on Indian language character recognition especially Kannada script among 15 major scripts in India. In this paper an attempt is made to recognize handwritten Kannada characters using Feed Forward neural networks. A handwritten Kannada character is resized into 20x30 Pixel. The resized character is used for training the neural network. Once the training process is completed the same character is given as input to the neural network with different set of neurons in hidden layer and their recognition accuracy rate for different Kannada characters has been calculated and compared. The results show that the proposed system yields good recognition accuracy rates comparable to that of other handwritten character recognition systems.
Parameter estimation using compensatory neural networks
Indian Academy of Sciences (India)
M Sinha; P K Kalra; K Kumar
2000-04-01
Proposed here is a new neuron model, a basis for Compensatory Neural Network Architecture (CNNA), which not only reduces the total number of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron model as well as the higher neuron model (multiplicative aggregation function). It can adapt to standard neuron and higher order neuron, as well as a combination of the two. This approach is found to estimate the orbit with accuracy significantly better than Kalman Filter (KF) and Feedforward Multilayer Neural Network (FMNN) (also simply referred to as Artificial Neural Network, ANN) with lambda-gamma learning. The typical simulation runs also bring out the superiority of the proposed scheme over Kalman filter from the standpoint of computation time and the amount of data needed for the desired degree of estimated accuracy for the specific problem of orbit determination.
Assessing Landslide Hazard Using Artificial Neural Network
DEFF Research Database (Denmark)
Farrokhzad, Farzad; Choobbasti, Asskar Janalizadeh; Barari, Amin
2011-01-01
neural network has been developed for use in the stability evaluation of slopes under various geological conditions and engineering requirements. The Artificial neural network model of this research uses slope characteristics as input and leads to the output in form of the probability of failure...... and factor of safety. It can be stated that the trained neural networks are capable of predicting the stability of slopes and safety factor of landslide hazard in study area with an acceptable level of confidence. Landslide hazard analysis and mapping can provide useful information for catastrophic loss...... failure" which is main concentration of the current research and "liquefaction failure". Shear failures along shear planes occur when the shear stress along the sliding surfaces exceed the effective shear strength. These slides have been referred to as landslide. An expert system based on artificial...
Recurrent Neural Network for Computing Outer Inverse.
Živković, Ivan S; Stanimirović, Predrag S; Wei, Yimin
2016-05-01
Two linear recurrent neural networks for generating outer inverses with prescribed range and null space are defined. Each of the proposed recurrent neural networks is based on the matrix-valued differential equation, a generalization of dynamic equations proposed earlier for the nonsingular matrix inversion, the Moore-Penrose inversion, as well as the Drazin inversion, under the condition of zero initial state. The application of the first approach is conditioned by the properties of the spectrum of a certain matrix; the second approach eliminates this drawback, though at the cost of increasing the number of matrix operations. The cases corresponding to the most common generalized inverses are defined. The conditions that ensure stability of the proposed neural network are presented. Illustrative examples present the results of numerical simulations.
Classification of radar clutter using neural networks.
Haykin, S; Deng, C
1991-01-01
A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar returns including weather, birds, and aircraft is described. The classifier achieves an average classification accuracy of 89% on generalization for data collected during a single scan of the radar antenna. The procedures of feature selection for neural network training, the classifier design considerations, the learning algorithm development, the implementation, and the experimental results of the neural clutter classifier, which is simulated on a Warp systolic computer, are discussed. A comparative evaluation of the multilayer neural network with a traditional Bayes classifier is presented.
Cotton genotypes selection through artificial neural networks.
Júnior, E G Silva; Cardoso, D B O; Reis, M C; Nascimento, A F O; Bortolin, D I; Martins, M R; Sousa, L B
2017-09-27
Breeding programs currently use statistical analysis to assist in the identification of superior genotypes at various stages of a cultivar's development. Differently from these analyses, the computational intelligence approach has been little explored in genetic improvement of cotton. Thus, this study was carried out with the objective of presenting the use of artificial neural networks as auxiliary tools in the improvement of the cotton to improve fiber quality. To demonstrate the applicability of this approach, this research was carried out using the evaluation data of 40 genotypes. In order to classify the genotypes for fiber quality, the artificial neural networks were trained with replicate data of 20 genotypes of cotton evaluated in the harvests of 2013/14 and 2014/15, regarding fiber length, uniformity of length, fiber strength, micronaire index, elongation, short fiber index, maturity index, reflectance degree, and fiber quality index. This quality index was estimated by means of a weighted average on the determined score (1 to 5) of each characteristic of the HVI evaluated, according to its industry standards. The artificial neural networks presented a high capacity of correct classification of the 20 selected genotypes based on the fiber quality index, so that when using fiber length associated with the short fiber index, fiber maturation, and micronaire index, the artificial neural networks presented better results than using only fiber length and previous associations. It was also observed that to submit data of means of new genotypes to the neural networks trained with data of repetition, provides better results of classification of the genotypes. When observing the results obtained in the present study, it was verified that the artificial neural networks present great potential to be used in the different stages of a genetic improvement program of the cotton, aiming at the improvement of the fiber quality of the future cultivars.
Neural networks and particle physics
Peterson, Carsten
1993-01-01
1. Introduction : Structure of the Central Nervous System Generics2. Feed-forward networks, Perceptions, Function approximators3. Self-organisation, Feature Maps4. Feed-back Networks, The Hopfield model, Optimization problems, Feed-back, Networks, Deformable templates, Graph bisection
Implementation aspects of Graph Neural Networks
Barcz, A.; Szymański, Z.; Jankowski, S.
2013-10-01
This article summarises the results of implementation of a Graph Neural Network classi er. The Graph Neural Network model is a connectionist model, capable of processing various types of structured data, including non- positional and cyclic graphs. In order to operate correctly, the GNN model must implement a transition function being a contraction map, which is assured by imposing a penalty on model weights. This article presents research results concerning the impact of the penalty parameter on the model training process and the practical decisions that were made during the GNN implementation process.
Livermore Big Artificial Neural Network Toolkit
Energy Technology Data Exchange (ETDEWEB)
2016-07-01
LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.
Human Face Recognition Using Convolutional Neural Networks
Directory of Open Access Journals (Sweden)
Răzvan-Daniel Albu
2009-10-01
Full Text Available In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. The convolutional network extracts successively larger features in a hierarchical set of layers. With the weights of the trained neural networks there are created kernel windows used for feature extraction in a 3-stage algorithm. I present experimental results illustrating the efficiency of the proposed approach. I use a database of 796 images of 159 individuals from Reims University which contains quite a high degree of variability in expression, pose, and facial details.
Spectral classification using convolutional neural networks
Hála, Pavel
2014-01-01
There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from one-dimension spectra only. Author developed several scripts and C programs for datasets preparation, preprocessing and postprocessing of the data. EBLearn library (developed by Pierre Sermanet and Yann LeCun) was used to create ConvNets. Application on dataset of more than 60000 spectra yielded success rate of nearly 95%. This thesis conclusively proved great potential of convolutional neural networks and deep learning methods in astrophysics.
Neural networks advances and applications 2
Gelenbe, E
1992-01-01
The present volume is a natural follow-up to Neural Networks: Advances and Applications which appeared one year previously. As the title indicates, it combines the presentation of recent methodological results concerning computational models and results inspired by neural networks, and of well-documented applications which illustrate the use of such models in the solution of difficult problems. The volume is balanced with respect to these two orientations: it contains six papers concerning methodological developments and five papers concerning applications and examples illustrating the theoret
SAR ATR Based on Convolutional Neural Network
Directory of Open Access Journals (Sweden)
Tian Zhuangzhuang
2016-06-01
Full Text Available This study presents a new method of Synthetic Aperture Radar (SAR image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recognition SAR datasets prove the validity of this method.
Contractor Prequalification Based on Neural Networks
Institute of Scientific and Technical Information of China (English)
ZHANG Jin-long; YANG Lan-rong
2002-01-01
Contractor Prequalification involves the screening of contractors by a project owner, according to a given set of criteria, in order to determine their competence to perform the work if awarded the construction contract. This paper introduces the capabilities of neural networks in solving problems related to contractor prequalification. The neural network systems for contractor prequalification has an input vector of 8 components and an output vector of 1 component. The output vector represents whether a contractor is qualified or not qualified to submit a bid on a project.
Simulation of photosynthetic production using neural network
Kmet, Tibor; Kmetova, Maria
2013-10-01
This paper deals with neural network based optimal control synthesis for solving optimal control problems with control and state constraints and discrete time delay. The optimal control problem is transcribed into nonlinear programming problem which is implemented with adaptive critic neural network. This approach is applicable to a wide class of nonlinear systems. The proposed simulation methods is illustrated by the optimal control problem of photosynthetic production described by discrete time delay differential equations. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
Top tagging with deep neural networks [Vidyo
CERN. Geneva
2017-01-01
Recent literature on deep neural networks for top tagging has focussed on image based techniques or multivariate approaches using high level jet substructure variables. Here, we take a sequential approach to this task by using anordered sequence of energy deposits as training inputs. Unlike previous approaches, this strategy does not result in a loss of information during pixelization or the calculation of high level features. We also propose new preprocessing methods that do not alter key physical quantities such as jet mass. We compare the performance of this approach to standard tagging techniques and present results evaluating the robustness of the neural network to pileup.
Intelligent neural network classifier for automatic testing
Bai, Baoxing; Yu, Heping
1996-10-01
This paper is concerned with an application of a multilayer feedforward neural network for the vision detection of industrial pictures, and introduces a high characteristics image processing and recognizing system which can be used for real-time testing blemishes, streaks and cracks, etc. on the inner walls of high-accuracy pipes. To take full advantage of the functions of the artificial neural network, such as the information distributed memory, large scale self-adapting parallel processing, high fault-tolerance ability, this system uses a multilayer perceptron as a regular detector to extract features of the images to be inspected and classify them.
Speech Recognition Method Based on Multilayer Chaotic Neural Network
Institute of Scientific and Technical Information of China (English)
REN Xiaolin; HU Guangrui
2001-01-01
In this paper,speech recognitionusing neural networks is investigated.Especially,chaotic dynamics is introduced to neurons,and a mul-tilayer chaotic neural network (MLCNN) architectureis built.A learning algorithm is also derived to trainthe weights of the network.We apply the MLCNNto speech recognition and compare the performanceof the network with those of recurrent neural net-work (RNN) and time-delay neural network (TDNN).Experimental results show that the MLCNN methodoutperforms the other neural networks methods withrespect to average recognition rate.
Directory of Open Access Journals (Sweden)
Onursal Çetin
2015-06-01
Full Text Available Objective: Implementation of multilayer neural network (MLNN with sigmoid activation function for the diagnosis of hepatitis disease. Methods: Artificial neural networks (ANNs are efficient tools currently in common use for medical diagnosis. In hardware based architectures activation functions play an important role in ANN behavior. Sigmoid function is the most frequently used activation function because of its smooth response. Thus, sigmoid function and its close approximations were implemented as activation function. The dataset is taken from the UCI machine learning database. Results: For the diagnosis of hepatitis disease, MLNN structure was implemented and Levenberg Morquardt (LM algorithm was used for learning. Our method of classifying hepatitis disease produced an accuracy of 91.9% to 93.8% via 10 fold cross validation. Conclusion: When compared to previous work that diagnosed hepatitis disease using artificial neural networks and the identical data set, our results are promising in order to reduce the size and cost of neural network based hardware. Thus, hardware based diagnosis systems can be developed effectively by using approximations of sigmoid function.
Multiprocessor Realization of Neural Networks
1990-04-01
the unique capabilities of receiving, processing, and transmitting electo-chemical signals. These signals are sent over neural pathways that make up...these switching nodes and a clever arrangement of internode links to guaranteee at least one’ path between each processor and memory. These types of
Optically excited synapse for neural networks.
Boyd, G D
1987-07-15
What can optics with its promise of parallelism do for neural networks which require matrix multipliers? An all optical approach requires optical logic devices which are still in their infancy. An alternative is to retain electronic logic while optically addressing the synapse matrix. This paper considers several versions of an optically addressed neural network compatible with VLSI that could be fabricated with the synapse connection unspecified. This optical matrix multiplier circuit is compared to an all electronic matrix multiplier. For the optical version a synapse consisting of back-to-back photodiodes is found to have a suitable i-v characteristic for optical matrix multiplication (a linear region) plus a clipping or nonlinear region as required for neural networks. Four photodiodes per synapse are required. The strength of the synapse connection is controlled by the optical power and is thus an adjustable parameter. The synapse network can be programmed in various ways such as a shadow mask of metal, imaged mask (static), or light valve or an acoustooptic scanned laser beam or array of beams (dynamic). A milliwatt from LEDs or lasers is adequate power. The neuron has a linear transfer function and is either a summing amplifier, in which case the synapse signal is current, or an integrator, in which case the synapse signal is charge, the choice of which depends on the programming mode. Optical addressing and settling times of microseconds are anticipated. Electronic neural networks using single-value resistor synapses or single-bit programmable synapses have been demonstrated in the high-gain region of discrete single-value feedback. As an alternative to these networks and the above proposed optical synapses, an electronic analog-voltage vector matrix multiplier is considered using MOSFETS as the variable conductance in CMOS VLSI. It is concluded that a shadow mask addressed (static) optical neural network is promising.
Porosity Log Prediction Using Artificial Neural Network
Dwi Saputro, Oki; Lazuardi Maulana, Zulfikar; Dzar Eljabbar Latief, Fourier
2016-08-01
Well logging is important in oil and gas exploration. Many physical parameters of reservoir is derived from well logging measurement. Geophysicists often use well logging to obtain reservoir properties such as porosity, water saturation and permeability. Most of the time, the measurement of the reservoir properties are considered expensive. One of method to substitute the measurement is by conducting a prediction using artificial neural network. In this paper, artificial neural network is performed to predict porosity log data from other log data. Three well from ‘yy’ field are used to conduct the prediction experiment. The log data are sonic, gamma ray, and porosity log. One of three well is used as training data for the artificial neural network which employ the Levenberg-Marquardt Backpropagation algorithm. Through several trials, we devise that the most optimal input training is sonic log data and gamma ray log data with 10 hidden layer. The prediction result in well 1 has correlation of 0.92 and mean squared error of 5.67 x10-4. Trained network apply to other well data. The result show that correlation in well 2 and well 3 is 0.872 and 0.9077 respectively. Mean squared error in well 2 and well 3 is 11 x 10-4 and 9.539 x 10-4. From the result we can conclude that sonic log and gamma ray log could be good combination for predicting porosity with neural network.
Autonomous robot behavior based on neural networks
Grolinger, Katarina; Jerbic, Bojan; Vranjes, Bozo
1997-04-01
The purpose of autonomous robot is to solve various tasks while adapting its behavior to the variable environment, expecting it is able to navigate much like a human would, including handling uncertain and unexpected obstacles. To achieve this the robot has to be able to find solution to unknown situations, to learn experienced knowledge, that means action procedure together with corresponding knowledge on the work space structure, and to recognize working environment. The planning of the intelligent robot behavior presented in this paper implements the reinforcement learning based on strategic and random attempts for finding solution and neural network approach for memorizing and recognizing work space structure (structural assignment problem). Some of the well known neural networks based on unsupervised learning are considered with regard to the structural assignment problem. The adaptive fuzzy shadowed neural network is developed. It has the additional shadowed hidden layer, specific learning rule and initialization phase. The developed neural network combines advantages of networks based on the Adaptive Resonance Theory and using shadowed hidden layer provides ability to recognize lightly translated or rotated obstacles in any direction.
Exploiting network redundancy for low-cost neural network realizations.
Keegstra, H; Jansen, WJ; Nijhuis, JAG; Spaanenburg, L; Stevens, H; Udding, JT
1996-01-01
A method is presented to optimize a trained neural network for physical realization styles. Target architectures are embedded microcontrollers or standard cell based ASIC designs. The approach exploits the redundancy in the network, required for successful training, to replace the synaptic weighting
Neutron spectrum unfolding using neural networks
Energy Technology Data Exchange (ETDEWEB)
Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E. [Universidad Autonoma de Zacatecas, A.P. 336, 98000 Zacatecas (Mexico)]. E-mail: rvega@cantera.reduaz.mx
2004-07-01
An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using a large set of neutron spectra compiled by the International Atomic Energy Agency. These include spectra from iso- topic neutron sources, reference and operational neutron spectra obtained from accelerators and nuclear reactors. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and correspondent spectrum was used as output during neural network training. The network has 7 input nodes, 56 neurons as hidden layer and 31 neurons in the output layer. After training the network was tested with the Bonner spheres count rates produced by twelve neutron spectra. The network allows unfolding the neutron spectrum from count rates measured with Bonner spheres. Good results are obtained when testing count rates belong to neutron spectra used during training, acceptable results are obtained for count rates obtained from actual neutron fields; however the network fails when count rates belong to monoenergetic neutron sources. (Author)
Embedded Streaming Deep Neural Networks Accelerator With Applications.
Dundar, Aysegul; Jin, Jonghoon; Martini, Berin; Culurciello, Eugenio
2016-04-08
Deep convolutional neural networks (DCNNs) have become a very powerful tool in visual perception. DCNNs have applications in autonomous robots, security systems, mobile phones, and automobiles, where high throughput of the feedforward evaluation phase and power efficiency are important. Because of this increased usage, many field-programmable gate array (FPGA)-based accelerators have been proposed. In this paper, we present an optimized streaming method for DCNNs' hardware accelerator on an embedded platform. The streaming method acts as a compiler, transforming a high-level representation of DCNNs into operation codes to execute applications in a hardware accelerator. The proposed method utilizes maximum computational resources available based on a novel-scheduled routing topology that combines data reuse and data concatenation. It is tested with a hardware accelerator implemented on the Xilinx Kintex-7 XC7K325T FPGA. The system fully explores weight-level and node-level parallelizations of DCNNs and achieves a peak performance of 247 G-ops while consuming less than 4 W of power. We test our system with applications on object classification and object detection in real-world scenarios. Our results indicate high-performance efficiency, outperforming all other presented platforms while running these applications.
Neural network and fuzzy control in FES-assisted locomotion for the hemiplegic.
Chen, Yu-Luen; Chen, Shih-Ching; Chen, Weoi-Luen; Hsiao, Chin-Chih; Kuo, Te-Son; Lai, Jin-Shin
2004-01-01
This study is aimed at establishing a neural network and fuzzy feedback control FES system used for adjusting the optimum electrical stimulating current to control the motion of an ankle joint. The proposed method further improves the drop-foot problem existing in hemiplegia patients. The proposed system includes both hardware and software. The hardware system determines the patient's ankle joint angle using a position sensor located in the patient's affected side. This sensor stimulates the tibialis anterior with an electrical stimulator that induces the dorsiflexion action and achieves the ideal ankle joint trace motion. The software system estimates the stimulating current using a neural network. The fuzzy controller solves the nonlinear problem by compensating the motion trace errors between the neural network control and actual system. The control qualities of various controllers for four subjects were compared in the clinical test. It was found that both the root mean square error and the mean error were minimal when using the neural network and fuzzy controller. The drop-foot problem in hemiplegic's locomotion was effectively improved by incorporating the neural network and fuzzy controller with the functional electrical simulator.
Analysis of Recurrent Analog Neural Networks
Directory of Open Access Journals (Sweden)
Z. Raida
1998-06-01
Full Text Available In this paper, an original rigorous analysis of recurrent analog neural networks, which are built from opamp neurons, is presented. The analysis, which comes from the approximate model of the operational amplifier, reveals causes of possible non-stable states and enables to determine convergence properties of the network. Results of the analysis are discussed in order to enable development of original robust and fast analog networks. In the analysis, the special attention is turned to the examination of the influence of real circuit elements and of the statistical parameters of processed signals to the parameters of the network.
Predicting Water Levels at Kainji Dam Using Artificial Neural Networks
African Journals Online (AJOL)
Predicting Water Levels at Kainji Dam Using Artificial Neural Networks. ... The aim of this study is to develop artificial neural network models for predicting water levels at Kainji Dam, which supplies water to Nigeria's largest ... Article Metrics.
Parameter Identification by Bayes Decision and Neural Networks
DEFF Research Database (Denmark)
Kulczycki, P.; Schiøler, Henrik
1994-01-01
The problem of parameter identification by Bayes point estimation using neural networks is investigated.......The problem of parameter identification by Bayes point estimation using neural networks is investigated....
Development of programmable artificial neural networks
Meade, Andrew J.
1993-01-01
Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed to mate the adaptability of the ANN with the speed and precision of the digital computer. This method was successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.
Sparse neural networks with large learning diversity
Gripon, Vincent
2011-01-01
Coded recurrent neural networks with three levels of sparsity are introduced. The first level is related to the size of messages, much smaller than the number of available neurons. The second one is provided by a particular coding rule, acting as a local constraint in the neural activity. The third one is a characteristic of the low final connection density of the network after the learning phase. Though the proposed network is very simple since it is based on binary neurons and binary connections, it is able to learn a large number of messages and recall them, even in presence of strong erasures. The performance of the network is assessed as a classifier and as an associative memory.
The labeled systems of multiple neural networks.
Nemissi, M; Seridi, H; Akdag, H
2008-08-01
This paper proposes an implementation scheme of K-class classification problem using systems of multiple neural networks. Usually, a multi-class problem is decomposed into simple sub-problems solved independently using similar single neural networks. For the reason that these sub-problems are not equivalent in their complexity, we propose a system that includes reinforced networks destined to solve complicated parts of the entire problem. Our approach is inspired from principles of the multi-classifiers systems and the labeled classification, which aims to improve performances of the networks trained by the Back-Propagation algorithm. We propose two implementation schemes based on both OAO (one-against-all) and OAA (one-against-one). The proposed models are evaluated using iris and human thigh databases.
Implementing Signature Neural Networks with Spiking Neurons
Directory of Open Access Journals (Sweden)
José Luis Carrillo-Medina
2016-12-01
Full Text Available Spiking Neural Networks constitute the most promising approach to develop realistic ArtificialNeural Networks (ANNs. Unlike traditional firing rate-based paradigms, information coding inspiking models is based on the precise timing of individual spikes. Spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition. In recent years, majorbreakthroughs in neuroscience research have discovered new relevant computational principles indifferent living neural systems. Could ANNs benefit from some of these recent findings providingnovel elements of inspiration? This is an intriguing question and the development of spiking ANNsincluding novel bio-inspired information coding and processing strategies is gaining attention. Fromthis perspective, in this work, we adapt the core concepts of the recently proposed SignatureNeural Network paradigm – i.e., neural signatures to identify each unit in the network, localinformation contextualization during the processing and multicoding strategies for informationpropagation regarding the origin and the content of the data – to be employed in a spiking neuralnetwork. To the best of our knowledge, none of these mechanisms have been used yet in thecontext of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicabilityin such networks. Computer simulations show that a simple network model like the discussed hereexhibits complex self-organizing properties. The combination of multiple simultaneous encodingschemes allows the network to generate coexisting spatio-temporal patterns of activity encodinginformation in different spatio-temporal spaces. As a function of the network and/or intra-unitparameters shaping the corresponding encoding modality, different forms of competition amongthe evoked patterns can emerge even in the absence of inhibitory connections. These parametersalso
Performance Comparison of Neural Networks for HRTFs Approximation
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
In order to approach to head-related transfer functions (HRTFs), this paper employs and compares three kinds of one-input neural network models, namely, multi-layer perceptron (MLP) networks, radial basis function (RBF) networks and wavelet neural networks (WNN) so as to select the best network model for further HRTFs approximation. Experimental results demonstrate that wavelet neural networks are more efficient and useful.
Applications of Neural Networks in Spinning Prediction
Institute of Scientific and Technical Information of China (English)
程文红; 陆凯
2003-01-01
The neural network spinning prediction model (BP and RBF Networks) trained by data from the mill can predict yarn qualities and spinning performance. The input parameters of the model are as follows: yarn count, diameter, hauteur, bundle strength, spinning draft, spinning speed, traveler number and twist.And the output parameters are: yarn evenness, thin places, tenacity and elongation, ends-down.Predicting results match the testing data well.
Temporal association in asymmetric neural networks
Sompolinsky, H.; Kanter, I.
1986-12-01
A neural network model which is capable of recalling time sequences and cycles of patterns is introduced. In this model, some of the synaptic connections, Jij, between pairs of neurons are asymmetric (Jij≠Jji) and have slow dynamic response. The effects of thermal noise on the generated sequences are discussed. Simulation results demonstrating the performance of the network are presented. The model may be also useful in understanding the generation of rhythmic patterns in biological motor systems.
Incremental construction of LSTM recurrent neural network
Ribeiro, Evandsa Sabrine Lopes-Lima; Alquézar Mancho, René
2002-01-01
Long Short--Term Memory (LSTM) is a recurrent neural network that uses structures called memory blocks to allow the net remember significant events distant in the past input sequence in order to solve long time lag tasks, where other RNN approaches fail. Throughout this work we have performed experiments using LSTM networks extended with growing abilities, which we call GLSTM. Four methods of training growing LSTM has been compared. These methods include cascade and ...
Stability and Adaptation of Neural Networks
1990-11-02
Feature discovery by competitive works.-~ IEEE Trans- Si’st.. Man. Cybern.. vol. SMC-13. pp. 815- learning.- Cogniive Science , vol. 9. pp. 75-112. 1985...include Electronic Engineering Times, the Los Angeles Times, Popular Science , the Economist, and Breakthroughs. As program chairman of the first...feedback neural networks.*’ Science . vol. 235. pp. 1226-1227. Mar. 6. 1987. networks.- submitted for publication. 141 G. A. Carpenter and S. Grossberg
Neural networks of human nature and nurture
Directory of Open Access Journals (Sweden)
Daniel S. Levine
2008-06-01
Full Text Available Neural network methods have facilitated the unifi - cation of several unfortunate splits in psychology, including nature versus nurture. We review the contributions of this methodology and then discuss tentative network theories of caring behavior, of uncaring behavior, and of how the frontal lobes are involved in the choices between them. The implications of our theory are optimistic about the prospects of society to encourage the human potential for caring.
Compressing Neural Networks with the Hashing Trick
Chen, Wenlin; Wilson, James T.; Tyree, Stephen; Weinberger, Kilian Q.; Chen, Yixin
2015-01-01
As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models. We present a novel network architecture, HashedNets, that exploits inherent redundancy in neural networks to achieve drastic reductions in model sizes. HashedNets uses a low-cost hash function to ...
Neural networks of human nature and nurture
Directory of Open Access Journals (Sweden)
Daniel S. Levine
2009-11-01
Full Text Available Neural network methods have facilitated the unification of several unfortunate splits in psychology, including nature versus nurture. We review the contributions of this methodology and then discuss tentative network theories of caring behavior, of uncaring behavior, and of how the frontal lobes are involved in the choices between them. The implications of our theory are optimistic about the prospects of society to encourage the human potential for caring.
Auto-associative nanoelectronic neural network
Energy Technology Data Exchange (ETDEWEB)
Nogueira, C. P. S. M.; Guimarães, J. G. [Departamento de Engenharia Elétrica - Laboratório de Dispositivos e Circuito Integrado, Universidade de Brasília, CP 4386, CEP 70904-970 Brasília DF (Brazil)
2014-05-15
In this paper, an auto-associative neural network using single-electron tunneling (SET) devices is proposed and simulated at low temperature. The nanoelectronic auto-associative network is able to converge to a stable state, previously stored during training. The recognition of the pattern involves decreasing the energy of the input state until it achieves a point of local minimum energy, which corresponds to one of the stored patterns.
Wireless Plug and Play Control Systems: Hardware, Networks, and Protocols
DEFF Research Database (Denmark)
Meybodi, Soroush Afkhami
2012-01-01
the protocols that can fulfill the stringent requirements of P3C case studies in general. In this part, after a thorough review of available Access and Routing protocols in industrial wireless networks, a combination of a deterministic Medium Access Control (MAC) protocol and a clustered flooding-based routing...... with the control topology. Functionality of the new routing metric is verified by simulations within a flooding-based routing algorithm. The results of this research project create a clear and concise interface for the other work packages of P3C which are concluded earlier....... the damp soil medium. To overcome the challenge, all potentially useful signal propagation methods are surveyed either by reviewing the open literature, or by doing simulations, or even running experiments. At the end, Magnetic Induction (MI) is chosen as the winning candidate. New findings are achieved...
Estimation of concrete compressive strength using artificial neural network
Kostić, Srđan; Vasović, Dejan
2015-01-01
In present paper, concrete compressive strength is evaluated using back propagation feed-forward artificial neural network. Training of neural network is performed using Levenberg-Marquardt learning algorithm for four architectures of artificial neural networks, one, three, eight and twelve nodes in a hidden layer in order to avoid the occurrence of overfitting. Training, validation and testing of neural network is conducted for 75 concrete samples with distinct w/c ratio and amount of superp...
Analysis of Wideband Beamformers Designed with Artificial Neural Networks
1990-12-01
TECHNICAL REPORT 0-90-1 ANALYSIS OF WIDEBAND BEAMFORMERS DESIGNED WITH ARTIFICIAL NEURAL NETWORKS by Cary Cox Instrumentation Services Division...included. A briel tutorial on beamformers and neural networks is also provided. 14. SUBJECT TERMS 15, NUMBER OF PAGES Artificial neural networks Fecdforwa:,l...Beamformers Designed with Artificial Neural Networks ". The study was conducted under the general supervision of Messrs. George P. Bonner, Chief
Neural network method for solving elastoplastic finite element problems
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
A basic optimization principle of Artificial Neural Network-the Lagrange Programming Neural Network (LPNN) model for solving elastoplastic finite element problems is presented. The nonlinear problems of mechanics are represented as a neural network based optimization problem by adopting the nonlinear function as nerve cell transfer function. Finally, two simple elastoplastic problems are numerically simulated. LPNN optimization results for elastoplastic problem are found to be comparable to traditional Hopfield neural network optimization model.
Combining logistic regression and neural networks to create predictive models.
Spackman, K. A.
1992-01-01
Neural networks are being used widely in medicine and other areas to create predictive models from data. The statistical method that most closely parallels neural networks is logistic regression. This paper outlines some ways in which neural networks and logistic regression are similar, shows how a small modification of logistic regression can be used in the training of neural network models, and illustrates the use of this modification for variable selection and predictive model building wit...
Dynamic Object Identification with SOM-based neural networks
Directory of Open Access Journals (Sweden)
Aleksey Averkin
2014-03-01
Full Text Available In this article a number of neural networks based on self-organizing maps, that can be successfully used for dynamic object identification, is described. Unique SOM-based modular neural networks with vector quantized associative memory and recurrent self-organizing maps as modules are presented. The structured algorithms of learning and operation of such SOM-based neural networks are described in details, also some experimental results and comparison with some other neural networks are given.
Remote Sensing Image Segmentation with Probabilistic Neural Networks
Institute of Scientific and Technical Information of China (English)
LIU Gang
2005-01-01
This paper focuses on the image segmentation with probabilistic neural networks (PNNs). Back propagation neural networks (BpNNs) and multi perceptron neural networks (MLPs) are also considered in this study. Especially, this paper investigates the implementation of PNNs in image segmentation and optimal processing of image segmentation with a PNN. The comparison between image segmentations with PNNs and with other neural networks is given. The experimental results show that PNNs can be successfully applied to image segmentation for good results.
Optimizing neural network models: motivation and case studies
Harp, S A; T. Samad
2012-01-01
Practical successes have been achieved with neural network models in a variety of domains, including energy-related industry. The large, complex design space presented by neural networks is only minimally explored in current practice. The satisfactory results that nevertheless have been obtained testify that neural networks are a robust modeling technology; at the same time, however, the lack of a systematic design approach implies that the best neural network models generally rem...
Hopfield Neural Network Approach to Clustering in Mobile Radio Networks
Institute of Scientific and Technical Information of China (English)
JiangYan; LiChengshu
1995-01-01
In this paper ,the Hopfield neural network(NN) algorithm is developed for selecting gateways in cluster linkage.The linked cluster(LC) architecture is assumed to achieve distributed network control in multihop radio networks throrgh the local controllers,called clusterheads and the nodes connecting these clusterheads are defined to be gateways.In Hopfield NN models ,the most critical issue being the determination of connection weights,we use the approach of Lagrange multipliers(LM) for its dynamic nature.
A Modified Algorithm for Feedforward Neural Networks
Institute of Scientific and Technical Information of China (English)
夏战国; 管红杰; 李政伟; 孟斌
2002-01-01
As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. And the simulation result illustrate the modified algorithm is more effective and practicable.
Convolutional Neural Networks for SAR Image Segmentation
DEFF Research Database (Denmark)
Malmgren-Hansen, David; Nobel-Jørgensen, Morten
2015-01-01
Segmentation of Synthetic Aperture Radar (SAR) images has several uses, but it is a difficult task due to a number of properties related to SAR images. In this article we show how Convolutional Neural Networks (CNNs) can easily be trained for SAR image segmentation with good results. Besides...
Psychometric Measurement Models and Artificial Neural Networks
Sese, Albert; Palmer, Alfonso L.; Montano, Juan J.
2004-01-01
The study of measurement models in psychometrics by means of dimensionality reduction techniques such as Principal Components Analysis (PCA) is a very common practice. In recent times, an upsurge of interest in the study of artificial neural networks apt to computing a principal component extraction has been observed. Despite this interest, the…
Applying Artificial Neural Networks for Face Recognition
Directory of Open Access Journals (Sweden)
Thai Hoang Le
2011-01-01
Full Text Available This paper introduces some novel models for all steps of a face recognition system. In the step of face detection, we propose a hybrid model combining AdaBoost and Artificial Neural Network (ABANN to solve the process efficiently. In the next step, labeled faces detected by ABANN will be aligned by Active Shape Model and Multi Layer Perceptron. In this alignment step, we propose a new 2D local texture model based on Multi Layer Perceptron. The classifier of the model significantly improves the accuracy and the robustness of local searching on faces with expression variation and ambiguous contours. In the feature extraction step, we describe a methodology for improving the efficiency by the association of two methods: geometric feature based method and Independent Component Analysis method. In the face matching step, we apply a model combining many Neural Networks for matching geometric features of human face. The model links many Neural Networks together, so we call it Multi Artificial Neural Network. MIT + CMU database is used for evaluating our proposed methods for face detection and alignment. Finally, the experimental results of all steps on CallTech database show the feasibility of our proposed model.
Artificial neural networks in neutron dosimetry
Energy Technology Data Exchange (ETDEWEB)
Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A. [Unidades Academicas de Estudios Nucleares, UAZ, A.P. 336, 98000 Zacatecas (Mexico); Gallego, E.; Lorente, A. [Depto. de Ingenieria Nuclear, Universidad Politecnica de Madrid, (Spain)
2005-07-01
An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the {chi}{sup 2}- test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)
Chaotic behavior of a layered neural network
Energy Technology Data Exchange (ETDEWEB)
Derrida, B.; Meir, R.
1988-09-15
We consider the evolution of configurations in a layered feed-forward neural network. Exact expressions for the evolution of the distance between two configurations are obtained in the thermodynamic limit. Our results show that the distance between two arbitrarily close configurations always increases, implying chaotic behavior, even in the phase of good retrieval.
Visualization of neural networks using saliency maps
DEFF Research Database (Denmark)
Mørch, Niels J.S.; Kjems, Ulrik; Hansen, Lars Kai
1995-01-01
The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations...
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...
Neural Networks for protein Structure Prediction
DEFF Research Database (Denmark)
Bohr, Henrik
1998-01-01
This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...
Nonlinear Time Series Analysis via Neural Networks
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Epileptiform spike detection via convolutional neural networks
DEFF Research Database (Denmark)
Johansen, Alexander Rosenberg; Jin, Jing; Maszczyk, Tomasz
2016-01-01
The EEG of epileptic patients often contains sharp waveforms called "spikes", occurring between seizures. Detecting such spikes is crucial for diagnosing epilepsy. In this paper, we develop a convolutional neural network (CNN) for detecting spikes in EEG of epileptic patients in an automated fash...
Learning chaotic attractors by neural networks
Bakker, R; Schouten, JC; Giles, CL; Takens, F; van den Bleek, CM
2000-01-01
An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time series. During training, the algorithm learns to short-term predict the time series. At the same time a criterion, developed by Diks, van Zwet, Takens, and de Goede (1996) is monitored th
Neural Networks for protein Structure Prediction
DEFF Research Database (Denmark)
Bohr, Henrik
1998-01-01
This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...
Binaural Sound Localization Using Neural Networks
1991-12-12
by Brennan, involved the implementation of a neural network to model the ability of a bat to discriminate between a mealworm and an inedible object...locate, identify and capture airborne prey (6:2). The sonar returns were collected from the mealworms , spheres and disks at various rotations (90 to
Brain tumor grading based on Neural Networks and Convolutional Neural Networks.
Yuehao Pan; Weimin Huang; Zhiping Lin; Wanzheng Zhu; Jiayin Zhou; Wong, Jocelyn; Zhongxiang Ding
2015-08-01
This paper studies brain tumor grading using multiphase MRI images and compares the results with various configurations of deep learning structure and baseline Neural Networks. The MRI images are used directly into the learning machine, with some combination operations between multiphase MRIs. Compared to other researches, which involve additional effort to design and choose feature sets, the approach used in this paper leverages the learning capability of deep learning machine. We present the grading performance on the testing data measured by the sensitivity and specificity. The results show a maximum improvement of 18% on grading performance of Convolutional Neural Networks based on sensitivity and specificity compared to Neural Networks. We also visualize the kernels trained in different layers and display some self-learned features obtained from Convolutional Neural Networks.
Neural networks in economic modelling : An empirical study
Verkooijen, W.J.H.
1996-01-01
This dissertation addresses the statistical aspects of neural networks and their usability for solving problems in economics and finance. Neural networks are discussed in a framework of modelling which is generally accepted in econometrics. Within this framework a neural network is regarded as a sta
Combining neural networks for protein secondary structure prediction
DEFF Research Database (Denmark)
Riis, Søren Kamaric
1995-01-01
In this paper structured neural networks are applied to the problem of predicting the secondary structure of proteins. A hierarchical approach is used where specialized neural networks are designed for each structural class and then combined using another neural network. The submodels are designe...... is better than most secondary structure prediction methods based on single sequences even though this model contains much fewer parameters...
Extracting Knowledge from Supervised Neural Networks in Image Procsssing
Zwaag, van der Berend Jan; Slump, Kees; Spaanenburg, Lambert; Jain, R.; Abraham, A.; Faucher, C.; Zwaag, van der B.J.
2003-01-01
Despite their success-story, artificial neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a ¿magic tool¿ but possibly even more as a my
Analysis of Neural Networks in Terms of Domain Functions
Zwaag, van der Berend Jan; Slump, Cees; Spaanenburg, Lambert
2002-01-01
Despite their success-story, artificial neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more as a my
Recognition of Continuous Digits by Quantum Neural Networks
Institute of Scientific and Technical Information of China (English)
无
2003-01-01
This paper describes a new kind of neural network-Quantum Neural Network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15 percent error reduction is achieved on a speaker-independent continuous digits recognition task compared with BP networks.
SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK
Institute of Scientific and Technical Information of China (English)
无
2003-01-01
For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.
A Fuzzy Neural Network for Fault Pattern Recognition
Institute of Scientific and Technical Information of China (English)
无
2001-01-01
This paper combines fuzzy set theory with AR T neural network, and demonstrates some important properties of the fuzzy ART neural network algorithm. The results from application on a ball bearing diagnosis indicate that a fuzzy ART neural network has an effect of fast stable recognition for fuzzy patterns.
A Direct Feedback Control Based on Fuzzy Recurrent Neural Network
Institute of Scientific and Technical Information of China (English)
李明; 马小平
2002-01-01
A direct feedback control system based on fuzzy-recurrent neural network is proposed, and a method of training weights of fuzzy-recurrent neural network was designed by applying modified contract mapping genetic algorithm. Computer simul ation results indicate that fuzzy-recurrent neural network controller has perfect dynamic and static performances .
[Application of artificial neural networks in infectious diseases].
Xu, Jun-fang; Zhou, Xiao-nong
2011-02-28
With the development of information technology, artificial neural networks has been applied to many research fields. Due to the special features such as nonlinearity, self-adaptation, and parallel processing, artificial neural networks are applied in medicine and biology. This review summarizes the application of artificial neural networks in the relative factors, prediction and diagnosis of infectious diseases in recent years.
Prediction based chaos control via a new neural network
Energy Technology Data Exchange (ETDEWEB)
Shen Liqun [School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001 (China)], E-mail: liqunshen@gmail.com; Wang Mao [Space Control and Inertia Technology Research Center, Harbin Institute of Technology, Harbin 150001 (China); Liu Wanyu [School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001 (China); Sun Guanghui [Space Control and Inertia Technology Research Center, Harbin Institute of Technology, Harbin 150001 (China)
2008-11-17
In this Letter, a new chaos control scheme based on chaos prediction is proposed. To perform chaos prediction, a new neural network architecture for complex nonlinear approximation is proposed. And the difficulty in building and training the neural network is also reduced. Simulation results of Logistic map and Lorenz system show the effectiveness of the proposed chaos control scheme and the proposed neural network.
Neural network method applied to particle image velocimetry
Grant, Ian; Pan, X.
1993-12-01
The last two decades have seen rapid developments in computing taking as their inspiration the human brain. The human brain functions in a highly parallel and distributed fashion. The adaptive structure of the brain means that learning or training can accompany decision making. This basic neural model has inspired computer hardware exhibiting a parallelism which has revolutionised processing speeds in complex task analysis. Similarly there has been substantial activity in the field of intelligent software and in particular in the area ofneural computing. The human brain may viewed as composed of approximately 1 dbasic units, the neurons. Each neuron exhibits a high degree of interconnectivity with connections to approximately 1 O other neurons. Each neuron accepts many inputs which are added or integrated in some fashion and this causes the neuron to become active or passive. The active neuron emits an output to interconnected neurons. The importance of any one input is controlled by the effectiveness of the corresponding interconnection or weight. One area that has attracted attention in the application of neural networks is pattern recognition. Here the functions of feature classification and extraction are handled by a network which receives some education or training prior to the task of recognition. A priori knowledge of expected outcomes is used as a starting point with the network being allowed to modify or enlarge its knowledge base as the task proceeds. Various models or approaches to adaptive problem solving have been developed. The pattern recognition problem considered in the present paper is the identification of image grouping in double exposure PIV images. The aim is to provide an adaptive net which, following initial training, is able to identify image partners and adapt to changing flow conditions. This latter feature is seen as essential in order that the full potential of the neural net in temporally or spatially changing flow regimes can be
From Designing A Single Neural Network to Designing Neural Network Ensembles
Institute of Scientific and Technical Information of China (English)
Liu Yong; Zou Xiu-fer
2003-01-01
This paper introduces supervised learning model,and surveys related research work. The paper is organised as follows. A supervised learning model is firstly described. The bias variance trade-off is then discussed for the supervised learning model. Based on the bias variance trade-off, both the single neural network approaches and the neural network en semble approaches are overviewed, and problems with the existing approaches are indicated. Finally, the paper concludes with specifying potential future research directions.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator
Directory of Open Access Journals (Sweden)
Jan Gosmann
2017-05-01
Full Text Available One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator.
Gosmann, Jan; Eliasmith, Chris
2017-01-01
One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install.
A Fuzzy Quantum Neural Network and Its Application in Pattern Recognition
Institute of Scientific and Technical Information of China (English)
MIAOFuyou; XIONGYan; CHENHuanhuan; WANGXingfu
2005-01-01
This paper proposes a fuzzy quantum neural network model combining quantum neural network and fuzzy logic, which applies the fuzzy logic to design the collapse rules of the quantum neural network, and solves the character recognition problem. Theoretical analysis and experimental results show that fuzzy quantum neural network improves recognizing veracity than the traditional neural network and quantum neural network.
Optical implementation of neural networks
Yu, Francis T. S.; Guo, Ruyan
2002-12-01
An adaptive optical neuro-computing (ONC) using inexpensive pocket size liquid crystal televisions (LCTVs) had been developed by the graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8×8=64 neurons, it can be easily extended to 16×20=320 neurons. The major advantages of this LCTV architecture as compared with other reported ONCs, are low cost and the flexibility to operate. To test the performance, several neural net models are used. These models are Interpattern Association, Hetero-association and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.
Distribution network planning algorithm based on Hopfield neural network
Institute of Scientific and Technical Information of China (English)
GAO Wei-xin; LUO Xian-jue
2005-01-01
This paper presents a new algorithm based on Hopfield neural network to find the optimal solution for an electric distribution network. This algorithm transforms the distribution power network-planning problem into a directed graph-planning problem. The Hopfield neural network is designed to decide the in-degree of each node and is in combined application with an energy function. The new algorithm doesn't need to code city streets and normalize data, so the program is easier to be realized. A case study applying the method to a district of 29 street proved that an optimal solution for the planning of such a power system could be obtained by only 26 iterations. The energy function and algorithm developed in this work have the following advantages over many existing algorithms for electric distribution network planning: fast convergence and unnecessary to code all possible lines.
Institute of Scientific and Technical Information of China (English)
ZhangLiangjie; LiYanda; 等
1997-01-01
In this paper,a dynamic bandwidth allocation technique based on fuzz neural networks(FNNs) and genetic algorithm(GA)is proposed for preventive congestion control in ATM network.The traffic model based on FNN does not need the descriptive traffic parameters in detail,which greatly depend on the user's terminal.Genetic algorithm is used to predict the equivalent bandwidth of the accepted traffic in real-time.Thus,the proposed scheme can estimate the dynamic bandwidth of the network in the time scale from the call arrival to the call admission/rejection due to the fuzzy-tech and GA hardware implementation.Simulation results show that the scheme can perform accurate dynamic bandwidth allocation to DN/OFF bursty traffic in accordance with the required quality of service(QOS),and the bandwidth utilization is improved from the overall point of view.
Neural networks in windprofiler data processing
Weber, H.; Richner, H.; Kretzschmar, R.; Ruffieux, D.
2003-04-01
Wind profilers are basically Doppler radars yielding 3-dimensional wind profiles that are deduced from the Doppler shift caused by turbulent elements in the atmosphere. These signals can be contaminated by other airborne elements such as birds or hydrometeors. Using a feed-forward neural network with one hidden layer and one output unit, birds and hydrometeors can be successfully identified in non-averaged single spectra; theses are subsequently removed in the wind computation. An infrared camera was used to identify birds in one of the beams of the wind profiler. After training the network with about 6000 contaminated data sets, it was able to identify contaminated data in a test data set with a reliability of 96 percent. The assumption was made that the neural network parameters obtained in the beam for which bird data was collected can be transferred to the other beams (at least three beams are needed for computing wind vectors). Comparing the evolution of a wind field with and without the neural network shows a significant improvement of wind data quality. Current work concentrates on training the network also for hydrometeors. It is hoped that the instrument's capability can thus be expanded to measure not only correct winds, but also observe bird migration, estimate precipitation and -- by combining precipitation information with vertical velocity measurement -- the monitoring of the height of the melting layer.
Color control of printers by neural networks
Tominaga, Shoji
1998-07-01
A method is proposed for solving the mapping problem from the 3D color space to the 4D CMYK space of printer ink signals by means of a neural network. The CIE-L*a*b* color system is used as the device-independent color space. The color reproduction problem is considered as the problem of controlling an unknown static system with four inputs and three outputs. A controller determines the CMYK signals necessary to produce the desired L*a*b* values with a given printer. Our solution method for this control problem is based on a two-phase procedure which eliminates the need for UCR and GCR. The first phase determines a neural network as a model of the given printer, and the second phase determines the combined neural network system by combining the printer model and the controller in such a way that it represents an identity mapping in the L*a*b* color space. Then the network of the controller part realizes the mapping from the L*a*b* space to the CMYK space. Practical algorithms are presented in the form of multilayer feedforward networks. The feasibility of the proposed method is shown in experiments using a dye sublimation printer and an ink jet printer.
Computationally Efficient Neural Network Intrusion Security Awareness
Energy Technology Data Exchange (ETDEWEB)
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
Reconstruction of periodic signals using neural networks
Directory of Open Access Journals (Sweden)
José Danilo Rairán Antolines
2014-01-01
Full Text Available In this paper, we reconstruct a periodic signal by using two neural networks. The first network is trained to approximate the period of a signal, and the second network estimates the corresponding coefficients of the signal's Fourier expansion. The reconstruction strategy consists in minimizing the mean-square error via backpro-pagation algorithms over a single neuron with a sine transfer function. Additionally, this paper presents mathematical proof about the quality of the approximation as well as a first modification of the algorithm, which requires less data to reach the same estimation; thus making the algorithm suitable for real-time implementations.
Computationally Efficient Neural Network Intrusion Security Awareness
Energy Technology Data Exchange (ETDEWEB)
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
The Stellar parametrization using Artificial Neural Network
Giridhar, Sunetra; Kunder, Andrea; Muneer, S; Kumar, G Selva
2012-01-01
An update on recent methods for automated stellar parametrization is given. We present preliminary results of the ongoing program for rapid parametrization of field stars using medium resolution spectra obtained using Vainu Bappu Telescope at VBO, Kavalur, India. We have used Artificial Neural Network for estimating temperature, gravity, metallicity and absolute magnitude of the field stars. The network for each parameter is trained independently using a large number of calibrating stars. The trained network is used for estimating atmospheric parameters of unexplored field stars.
Neural networks: Application to medical imaging
Clarke, Laurence P.
1994-01-01
The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.
a Heterosynaptic Learning Rule for Neural Networks
Emmert-Streib, Frank
In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.
Neural network for sonogram gap filling
DEFF Research Database (Denmark)
Klebæk, Henrik; Jensen, Jørgen Arendt; Hansen, Lars Kai
1995-01-01
. The neural network is trained on part of the data and the network is pruned by the optimal brain damage procedure in order to reduce the number of parameters in the network, and thereby reduce the risk of overfitting. The neural predictor is compared to using a linear filter for the mean and variance time......In duplex imaging both an anatomical B-mode image and a sonogram are acquired, and the time for data acquisition is divided between the two images. This gives problems when rapid B-mode image display is needed, since there is not time for measuring the velocity data. Gaps then appear...... in the sonogram and in the audio signal, rendering the audio signal useless, thus making diagnosis difficult. The current goal for ultrasound scanners is to maintain a high refresh rate for the B-mode image and at the same time attain a high maximum velocity in the sonogram display. This precludes the intermixing...
Fuzzy logic and neural network technologies
Villarreal, James A.; Lea, Robert N.; Savely, Robert T.
1992-01-01
Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.
Design of Robust Neural Network Classifiers
DEFF Research Database (Denmark)
Larsen, Jan; Andersen, Lars Nonboe; Hintz-Madsen, Mads
1998-01-01
a modified likelihood function which incorporates the potential risk of outliers in the data. This leads to the introduction of a new parameter, the outlier probability. Designing the neural classifier involves optimization of network weights as well as outlier probability and regularization parameters. We...... suggest to adapt the outlier probability and regularisation parameters by minimizing the error on a validation set, and a simple gradient descent scheme is derived. In addition, the framework allows for constructing a simple outlier detector. Experiments with artificial data demonstrate the potential......This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the log-likelihood and a regularization term (prior). In order to perform robust classification, we present...
Interfacing Hardware Accelerators to a Time-Division Multiplexing Network-on-Chip
DEFF Research Database (Denmark)
Pezzarossa, Luca; Sørensen, Rasmus Bo; Schoeberl, Martin
2015-01-01
This paper addresses the integration of stateless hardware accelerators into time-predictable multi-core platforms based on time-division multiplexing networks-on-chip. Stateless hardware accelerators, like floating-point units, are typically attached as co-processors to individual processors in ...... implementation. The design evaluation is carried out using the open source T-CREST multi-core platform implemented on an Altera Cyclone IV FPGA. The size of the proposed design, including a floating-point accelerator, is about two-thirds of a processor....
The loading problem for recursive neural networks.
Gori, Marco; Sperduti, Alessandro
2005-10-01
The present work deals with one of the major and not yet completely understood topics of supervised connectionist models. Namely, it investigates the relationships between the difficulty of a given learning task and the chosen neural network architecture. These relationships have been investigated and nicely established for some interesting problems in the case of neural networks used for processing vectors and sequences, but only a few studies have dealt with loading problems involving graphical inputs. In this paper, we present sufficient conditions which guarantee the absence of local minima of the error function in the case of learning directed acyclic graphs with recursive neural networks. We introduce topological indices which can be directly calculated from the given training set and that allows us to design the neural architecture with local minima free error function. In particular, we conceive a reduction algorithm that involves both the information attached to the nodes and the topology, which enlarges significantly the class of the problems with unimodal error function previously proposed in the literature.
Inference and contradictory analysis for binary neural networks
Institute of Scientific and Technical Information of China (English)
郭宝龙; 郭雷
1996-01-01
A weak-inference theory and a contradictory analysis for binary neural networks (BNNs).are presented.The analysis indicates that the essential reason why a neural network is changing its slates is the existence of superior contradiction inside the network,and that the process by which a neural network seeks a solution corresponds to eliminating the superior contradiction.Different from general constraint satisfaction networks,the solutions found by BNNs may contain inferior contradiction but not superior contradiction.
Clustering in mobile ad hoc network based on neural network
Institute of Scientific and Technical Information of China (English)
CHEN Ai-bin; CAI Zi-xing; HU De-wen
2006-01-01
An on-demand distributed clustering algorithm based on neural network was proposed. The system parameters and the combined weight for each node were computed, and cluster-heads were chosen using the weighted clustering algorithm, then a training set was created and a neural network was trained. In this algorithm, several system parameters were taken into account, such as the ideal node-degree, the transmission power, the mobility and the battery power of the nodes. The algorithm can be used directly to test whether a node is a cluster-head or not. Moreover, the clusters recreation can be speeded up.
Pruning Neural Networks with Distribution Estimation Algorithms
Energy Technology Data Exchange (ETDEWEB)
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Phase Diagram of Spiking Neural Networks
Directory of Open Access Journals (Sweden)
Hamed eSeyed-Allaei
2015-03-01
Full Text Available In computer simulations of spiking neural networks, often it is assumed that every two neurons of the network are connected by a probablilty of 2%, 20% of neurons are inhibitory and 80% are excitatory. These common values are based on experiments, observations. but here, I take a different perspective, inspired by evolution. I simulate many networks, each with a different set of parameters, and then I try to figure out what makes the common values desirable by nature. Networks which are configured according to the common values, have the best dynamic range in response to an impulse and their dynamic range is more robust in respect to synaptic weights. In fact, evolution has favored networks of best dynamic range. I present a phase diagram that shows the dynamic ranges of different networks of different parameteres. This phase diagram gives an insight into the space of parameters -- excitatory to inhibitory ratio, sparseness of connections and synaptic weights. It may serve as a guideline to decide about the values of parameters in a simulation of spiking neural network.
Gait Recognition Based on Convolutional Neural Networks
Sokolova, A.; Konushin, A.
2017-05-01
In this work we investigate the problem of people recognition by their gait. For this task, we implement deep learning approach using the optical flow as the main source of motion information and combine neural feature extraction with the additional embedding of descriptors for representation improvement. In order to find the best heuristics, we compare several deep neural network architectures, learning and classification strategies. The experiments were made on two popular datasets for gait recognition, so we investigate their advantages and disadvantages and the transferability of considered methods.
Code generation: a strategy for neural network simulators.
Goodman, Dan F M
2010-10-01
We demonstrate a technique for the design of neural network simulation software, runtime code generation. This technique can be used to give the user complete flexibility in specifying the mathematical model for their simulation in a high level way, along with the speed of code written in a low level language such as C+ +. It can also be used to write code only once but target different hardware platforms, including inexpensive high performance graphics processing units (GPUs). Code generation can be naturally combined with computer algebra systems to provide further simplification and optimisation of the generated code. The technique is quite general and could be applied to any simulation package. We demonstrate it with the 'Brian' simulator ( http://www.briansimulator.org ).
Efficiently passing messages in distributed spiking neural network simulation.
Thibeault, Corey M; Minkovich, Kirill; O'Brien, Michael J; Harris, Frederick C; Srinivasa, Narayan
2013-01-01
Efficiently passing spiking messages in a neural model is an important aspect of high-performance simulation. As the scale of networks has increased so has the size of the computing systems required to simulate them. In addition, the information exchange of these resources has become more of an impediment to performance. In this paper we explore spike message passing using different mechanisms provided by the Message Passing Interface (MPI). A specific implementation, MVAPICH, designed for high-performance clusters with Infiniband hardware is employed. The focus is on providing information about these mechanisms for users of commodity high-performance spiking simulators. In addition, a novel hybrid method for spike exchange was implemented and benchmarked.
Cellular Neural Networks for NP-Hard Optimization
Directory of Open Access Journals (Sweden)
Mária Ercsey-Ravasz
2009-02-01
Full Text Available A cellular neural/nonlinear network (CNN is used for NP-hard optimization. We prove that a CNN in which the parameters of all cells can be separately controlled is the analog correspondent of a two-dimensional Ising-type (Edwards-Anderson spin-glass system. Using the properties of CNN, we show that one single operation (template always yields a local minimum of the spin-glass energy function. This way, a very fast optimization method, similar to simulated annealing, can be built. Estimating the simulation time needed on CNN-based computers, and comparing it with the time needed on normal digital computers using the simulated annealing algorithm, the results are astonishing. CNN computers could be faster than digital computers already at 10×10 lattice sizes. The local control of the template parameters was already partially realized on some of the hardwares, we think this study could further motivate their development in this direction.
Hopfield neural network implementation of the optimal CDMA multiuser detector.
Kechriotis, G I; Manolakos, E S
1996-01-01
We investigate the application of Hopfield neural networks (HNN's) to the problem of multiuser detection in spread spectrum/CDMA (code division multiple access) communication systems. It is shown that the NP-complete problem of minimizing the objective function of the optimal multiuser detector (OMD) can be translated into minimizing an HNN "energy" function, thus allowing to take advantage of the ability of HNN's to perform very fast gradient descent algorithms in analog hardware and produce in real-time suboptimal solutions to hard combinatorial optimization problems. The performance of the proposed HNN receiver is evaluated via computer simulations and compared to that of other suboptimal schemes as well as to that of the OMD for both the synchronous and the asynchronous CDMA transmission cases. It is shown that the HNN detector exhibits a number of attractive properties and that it provides a powerful generalization of a well-known and extensively studied suboptimal scheme, namely the multistage detector.
Efficiently passing messages in distributed spiking neural network simulation
Directory of Open Access Journals (Sweden)
Corey Michael Thibeault
2013-06-01
Full Text Available Efficiently passing spiking messages in a neural model is an important aspect of high-performance simulation. As the scale of networks has increased so has the size of the computing systems required to simulate them. In addition, the information exchange of these resources has become more of an impediment to performance. In this paper we explore spike message passing using different mechanisms provided by the Message Passing Interface (MPI. A specific implementation, MVAPICH, designed for high-performance clusters with Infiniband hardware is employed. The focus is on providing information about these mechanisms for users of commodity high-performance spiking simulators. In addition, a novel hybrid-method for spike exchange was implemented and benchmarked.
Fuzzy logic and neural networks basic concepts & application
Alavala, Chennakesava R
2008-01-01
About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank
Cancer classification based on gene expression using neural networks.
Hu, H P; Niu, Z J; Bai, Y P; Tan, X H
2015-12-21
Based on gene expression, we have classified 53 colon cancer patients with UICC II into two groups: relapse and no relapse. Samples were taken from each patient, and gene information was extracted. Of the 53 samples examined, 500 genes were considered proper through analyses by S-Kohonen, BP, and SVM neural networks. Classification accuracy obtained by S-Kohonen neural network reaches 91%, which was more accurate than classification by BP and SVM neural networks. The results show that S-Kohonen neural network is more plausible for classification and has a certain feasibility and validity as compared with BP and SVM neural networks.
Brüderle, Daniel; Petrovici, Mihai A; Vogginger, Bernhard; Ehrlich, Matthias; Pfeil, Thomas; Millner, Sebastian; Grübl, Andreas; Wendt, Karsten; Müller, Eric; Schwartz, Marc-Olivier; de Oliveira, Dan Husmann; Jeltsch, Sebastian; Fieres, Johannes; Schilling, Moritz; Müller, Paul; Breitwieser, Oliver; Petkov, Venelin; Muller, Lyle; Davison, Andrew P; Krishnamurthy, Pradeep; Kremkow, Jens; Lundqvist, Mikael; Muller, Eilif; Partzsch, Johannes; Scholze, Stefan; Zühl, Lukas; Mayr, Christian; Destexhe, Alain; Diesmann, Markus; Potjans, Tobias C; Lansner, Anders; Schüffny, René; Schemmel, Johannes; Meier, Karlheinz
2011-05-01
In this article, we present a methodological framework that meets novel requirements emerging from upcoming types of accelerated and highly configurable neuromorphic hardware systems. We describe in detail a device with 45 million programmable and dynamic synapses that is currently under development, and we sketch the conceptual challenges that arise from taking this platform into operation. More specifically, we aim at the establishment of this neuromorphic system as a flexible and neuroscientifically valuable modeling tool that can be used by non-hardware experts. We consider various functional aspects to be crucial for this purpose, and we introduce a consistent workflow with detailed descriptions of all involved modules that implement the suggested steps: The integration of the hardware interface into the simulator-independent model description language PyNN; a fully automated translation between the PyNN domain and appropriate hardware configurations; an executable specification of the future neuromorphic system that can be seamlessly integrated into this biology-to-hardware mapping process as a test bench for all software layers and possible hardware design modifications; an evaluation scheme that deploys models from a dedicated benchmark library, compares the results generated by virtual or prototype hardware devices with reference software simulations and analyzes the differences. The integration of these components into one hardware-software workflow provides an ecosystem for ongoing preparative studies that support the hardware design process and represents the basis for the maturity of the model-to-hardware mapping software. The functionality and flexibility of the latter is proven with a variety of experimental results.
Hardware in Loop Simulation for Emergency Communication Mobile Ad Hoc Network
Institute of Scientific and Technical Information of China (English)
YANG Jie; AN Jian-ping; LIU Heng
2007-01-01
For the research of mobile Ad hoc network (MANET), hardware in the loop simulation (HILS) is introduced to improve simulation fidelity. The architectures and frameworks of HILS system are discussed. Based on HILS and QualNet network simulator, two kinds of simulation frameworks for MANET multicast emergency communicati on network are proposed. By running simulation under this configuration and doing experiments with on-demand multicast routing protocol (ODMRP), unicast and multicast functions of this protocol are tested. Research results indicate that HILS method can effectively reduce the difficulty of system modeling and improve precision of simulation, and can further accelerate transition from design to system deployment.
Functional expansion representations of artificial neural networks
Gray, W. Steven
1992-01-01
In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.
Convolutional Neural Network Based dem Super Resolution
Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang
2016-06-01
DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.
Chemical implementation of neural networks and Turing machines.
Hjelmfelt, A; Weinberger, E D; Ross, J
1991-01-01
We propose a reversible reaction mechanism with a single stationary state in which certain concentrations assume either high or low values dependent on the concentration of a catalyst. The properties of this mechanism are those of a McCulloch-Pitts neuron. We suggest a mechanism of interneuronal connections in which the stationary state of a chemical neuron is determined by the state of other neurons in a homogeneous chemical system and is thus a "hardware" chemical implementation of neural networks. Specific connections are determined for the construction of logic gates: AND, NOR, etc. Neural networks may be constructed in which the flow of time is continuous and computations are achieved by the attainment of a stationary state of the entire chemical reaction system, or in which the flow of time is discretized by an oscillatory reaction. In another article, we will give a chemical implementation of finite state machines and stack memories, with which in principle the construction of a universal Turing machine is possible. PMID:1763012
Chemical Implementation of Neural Networks and Turing Machines
Hjelmfelt, Allen; Weinberger, Edward D.; Ross, John
1991-12-01
We propose a reversible reaction mechanism with a single stationary state in which certain concentrations assume either high or low values dependent on the concentration of a catalyst. The properties of this mechanism are those of a McCulloch-Pitts neuron. We suggest a mechanism of interneuronal connections in which the stationary state of a chemical neuron is determined by the state of other neurons in a homogeneous chemical system and is thus a "hardware" chemical implementation of neural networks. Specific connections are determined for the construction of logic gates: AND, NOR, etc. Neural networks may be constructed in which the flow of time is continuous and computations are achieved by the attainment of a stationary state of the entire chemical reaction system, or in which the flow of time is discretized by an oscillatory reaction. In another article, we will give a chemical implementation of finite state machines and stack memories, with which in principle the construction of a universal Turing machine is possible.
Chemical implementation of neural networks and Turing machines.
Hjelmfelt, A; Weinberger, E D; Ross, J
1991-12-15
We propose a reversible reaction mechanism with a single stationary state in which certain concentrations assume either high or low values dependent on the concentration of a catalyst. The properties of this mechanism are those of a McCulloch-Pitts neuron. We suggest a mechanism of interneuronal connections in which the stationary state of a chemical neuron is determined by the state of other neurons in a homogeneous chemical system and is thus a "hardware" chemical implementation of neural networks. Specific connections are determined for the construction of logic gates: AND, NOR, etc. Neural networks may be constructed in which the flow of time is continuous and computations are achieved by the attainment of a stationary state of the entire chemical reaction system, or in which the flow of time is discretized by an oscillatory reaction. In another article, we will give a chemical implementation of finite state machines and stack memories, with which in principle the construction of a universal Turing machine is possible.
Toward implementation of artificial neural networks that "really work".
Leon, M. A.; Keller, J.
1997-01-01
Artificial neural networks are established analytical methods in bio-medical research. They have repeatedly outperformed traditional tools for pattern recognition and clinical outcome prediction while assuring continued adaptation and learning. However, successful experimental neural networks systems seldom reach a production state. That is, they are not incorporated into clinical information systems. It could be speculated that neural networks simply must undergo a lengthy acceptance process before they become part of the day to day operations of health care systems. However, our experience trying to incorporate experimental neural networks into information systems lead us to believe that there are technical and operational barriers that greatly difficult neural network implementation. A solution for these problems may be the delineation of policies and procedures for neural network implementation and the development a new class of neural network client/server applications that fit the needs of current clinical information systems. PMID:9357613
Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents
Sher, Gene I
2011-01-01
Though machine learning has been applied to the foreign exchange market for quiet some time now, and neural networks have been shown to yield good results, in modern approaches neural network systems are optimized through the traditional methods, and their input signals are vectors containing prices and other indicator elements. The aim of this paper is twofold, the presentation and testing of the application of topology and weight evolving artificial neural network (TWEANN) systems to automated currency trading, and the use of chart images as input to a geometrical regularity aware indirectly encoded neural network systems. This paper presents the benchmark results of neural network based automated currency trading systems evolved using TWEANNs, and compares the generalization capabilities of these direct encoded neural networks which use the standard price vector inputs, and the indirect (substrate) encoded neural networks which use chart images as input. The TWEANN algorithm used to evolve these currency t...
A Projection Neural Network for Constrained Quadratic Minimax Optimization.
Liu, Qingshan; Wang, Jun
2015-11-01
This paper presents a projection neural network described by a dynamic system for solving constrained quadratic minimax programming problems. Sufficient conditions based on a linear matrix inequality are provided for global convergence of the proposed neural network. Compared with some of the existing neural networks for quadratic minimax optimization, the proposed neural network in this paper is capable of solving more general constrained quadratic minimax optimization problems, and the designed neural network does not include any parameter. Moreover, the neural network has lower model complexities, the number of state variables of which is equal to that of the dimension of the optimization problems. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural network.
Open-source hardware and software and web application for gamma dose rate network operation.
Luff, R; Zähringer, M; Harms, W; Bleher, M; Prommer, B; Stöhlker, U
2014-08-01
The German Federal Office for Radiation Protection operates a network of about 1800 gamma dose rate stations as a part of the national emergency preparedness plan. Each of the six network centres is capable of operating the network alone. Most of the used hardware and software have been developed in-house under open-source license. Short development cycles and close cooperation between developers and users ensure robustness, transparency and fast maintenance procedures, thus avoiding unnecessary complex solutions. This also reduces the overall costs of the network operation. An easy-to-expand web interface has been developed to make the complete system available to other interested network operators in order to increase cooperation between different countries. The interface is also regularly in use for education during scholarships of trainees supported, e.g. by the 'International Atomic Energy Agency' to operate a local area dose rate monitoring test network.
Neural network models of categorical perception.
Damper, R I; Harnad, S R
2000-05-01
Studies of the categorical perception (CP) of sensory continua have a long and rich history in psychophysics. In 1977, Macmillan, Kaplan, and Creelman introduced the use of signal detection theory to CP studies. Anderson and colleagues simultaneously proposed the first neural model for CP, yet this line of research has been less well explored. In this paper, we assess the ability of neural-network models of CP to predict the psychophysical performance of real observers with speech sounds and artificial/novel stimuli. We show that a variety of neural mechanisms are capable of generating the characteristics of CP. Hence, CP may not be a special model of perception but an emergent property of any sufficiently powerful general learning system.
Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS
Directory of Open Access Journals (Sweden)
Christopher Bergmeir
2012-01-01
Full Text Available Neural networks are important standard machine learning procedures for classification and regression. We describe the R package RSNNS that provides a convenient interface to the popular Stuttgart Neural Network Simulator SNNS. The main features are (a encapsulation of the relevant SNNS parts in a C++ class, for sequential and parallel usage of different networks, (b accessibility of all of the SNNSalgorithmic functionality from R using a low-level interface, and (c a high-level interface for convenient, R-style usage of many standard neural network procedures. The package also includes functions for visualization and analysis of the models and the training procedures, as well as functions for data input/output from/to the original SNNSfile formats.
Development of Polymer Resins using Neural Networks
Directory of Open Access Journals (Sweden)
Fabiano A. N. Fernandes
2002-01-01
Full Text Available The development of polymer resins can benefit from the application of neural networks, using its great ability to correlate inputs and outputs. In this work we have developed a procedure that uses neural networks to correlate the end-user properties of a polymer with the polymerization reactor's operational condition that will produce that desired polymer. This procedure is aimed at speeding up the development of new resins and help finding the appropriate operational conditions to produce a given polymer resin; reducing experimentation, pilot plant tests and therefore time and money spent on development. The procedure shown in this paper can predict the reactor's operational condition with an error lower than 5%.
Neural network correction of astrometric chromaticity
Gai, M
2005-01-01
In this paper we deal with the problem of chromaticity, i.e. apparent position variation of stellar images with their spectral distribution, using neural networks to analyse and process astronomical images. The goal is to remove this relevant source of systematic error in the data reduction of high precision astrometric experiments, like Gaia. This task can be accomplished thanks to the capability of neural networks to solve a nonlinear approximation problem, i.e. to construct an hypersurface that approximates a given set of scattered data couples. Images are encoded associating each of them with conveniently chosen moments, evaluated along the y axis. The technique proposed, in the current framework, reduces the initial chromaticity of few milliarcseconds to values of few microarcseconds.
Web Page Categorization Using Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Web page categorization is one of the challenging tasks in the world of ever increasing web technologies. There are many ways of categorization of web pages based on different approach and features. This paper proposes a new dimension in the way of categorization of web pages using artificial neural network (ANN) through extracting the features automatically. Here eight major categories of web pages have been selected for categorization; these are business & economy, education, government, entertainment, sports, news & media, job search, and science. The whole process of the proposed system is done in three successive stages. In the first stage, the features are automatically extracted through analyzing the source of the web pages. The second stage includes fixing the input values of the neural network; all the values remain between 0 and 1. The variations in those values affect the output. Finally the third stage determines the class of a certain web page out of eight predefined classes. This stage i...
Neural networks for aerosol particles characterization
Berdnik, V. V.; Loiko, V. A.
2016-11-01
Multilayer perceptron neural networks with one, two and three inputs are built to retrieve parameters of spherical homogeneous nonabsorbing particle. The refractive index ranges from 1.3 to 1.7; particle radius ranges from 0.251 μm to 56.234 μm. The logarithms of the scattered radiation intensity are used as input signals. The problem of the most informative scattering angles selection is elucidated. It is shown that polychromatic illumination helps one to increase significantly the retrieval accuracy. In the absence of measurement errors relative error of radius retrieval by the neural network with three inputs is 0.54%, relative error of the refractive index retrieval is 0.84%. The effect of measurement errors on the result of retrieval is simulated.
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, Alex
2012-01-01
Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools—robust to input noise and distortion, able to exploit long-range contextual information—that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary. The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional...
Neural Network Program Package for Prosody Modeling
Directory of Open Access Journals (Sweden)
J. Santarius
2004-04-01
Full Text Available This contribution describes the programme for one part of theautomatic Text-to-Speech (TTS synthesis. Some experiments (for example[14] documented the considerable improvement of the naturalness ofsynthetic speech, but this approach requires completing the inputfeature values by hand. This completing takes a lot of time for bigfiles. We need to improve the prosody by other approaches which useonly automatically classified features (input parameters. Theartificial neural network (ANN approach is used for the modeling ofprosody parameters. The program package contains all modules necessaryfor the text and speech signal pre-processing, neural network training,sensitivity analysis, result processing and a module for the creationof the input data protocol for Czech speech synthesizer ARTIC [1].
Face Recognition using Eigenfaces and Neural Networks
Directory of Open Access Journals (Sweden)
Mohamed Rizon
2006-01-01
Full Text Available In this study, we develop a computational model to identify the face of an unknown persons by applying eigenfaces. The eigenfaces has been applied to extract the basic face of the human face images. The eigenfaces is then projecting onto human faces to identify unique features vectors. This significant features vector can be used to identify an unknown face by using the backpropagation neural network that utilized euclidean distance for classification and recognition. The ORL database for this investigation consists of 40 people with various 400 face images had been used for the learning. The eigenfaces including implemented Jacobis method for eigenvalues and eigenvectors has been performed. The classification and recognition using backpropagation neural network showed impressive positive result to classify face images.
Hierarchical Neural Network Structures for Phoneme Recognition
Vasquez, Daniel; Minker, Wolfgang
2013-01-01
In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.
Multi-Dimensional Recurrent Neural Networks
Graves, Alex; Schmidhuber, Juergen
2007-01-01
Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to input warping, and the ability to access contextual information, are also desirable in multidimensional domains. However, there has so far been no direct way of applying RNNs to data with more than one spatio-temporal dimension. This paper introduces multi-dimensional recurrent neural networks (MDRNNs), thereby extending the potential applicability of RNNs to vision, video processing, medical imaging and many other areas, while avoiding the scaling problems that have plagued other multi-dimensional models. Experimental results are provided for two image segmentation tasks.
On analog implementations of discrete neural networks
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.; Moore, K.R.
1998-12-01
The paper will show that in order to obtain minimum size neural networks (i.e., size-optimal) for implementing any Boolean function, the nonlinear activation function of the neutrons has to be the identity function. The authors shall shortly present many results dealing with the approximation capabilities of neural networks, and detail several bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions they will show that implementing Boolean functions can be done using neurons having an identity nonlinear function. It follows that size-optimal solutions can be obtained only using analog circuitry. Conclusions, and several comments on the required precision are ending the paper.
Applying neural networks to optimize instrumentation performance
Energy Technology Data Exchange (ETDEWEB)
Start, S.E.; Peters, G.G.
1995-06-01
Well calibrated instrumentation is essential in providing meaningful information about the status of a plant. Signals from plant instrumentation frequently have inherent non-linearities, may be affected by environmental conditions and can therefore cause calibration difficulties for the people who maintain them. Two neural network approaches are described in this paper for improving the accuracy of a non-linear, temperature sensitive level probe ised in Expermental Breeder Reactor II (EBR-II) that was difficult to calibrate.
Identifying Tracks Duplicates via Neural Network
Sunjerga, Antonio; CERN. Geneva. EP Department
2017-01-01
The goal of the project is to study feasibility of state of the art machine learning techniques in track reconstruction. Machine learning techniques provide promising ways to speed up the pattern recognition of tracks by adding more intelligence in the algorithms. Implementation of neural network to process of track duplicates identifying will be discussed. Different approaches are shown and results are compared to method that is currently in use.
Neural Network-Based Hyperspectral Algorithms
2016-06-07
Neural Network-Based Hyperspectral Algorithms Walter F. Smith, Jr. and Juanita Sandidge Naval Research Laboratory Code 7340, Bldg 1105 Stennis Space...our effort is development of robust numerical inversion algorithms , which will retrieve inherent optical properties of the water column as well as...validate the resulting inversion algorithms with in-situ data and provide estimates of the error bounds associated with the inversion algorithm . APPROACH
Diagnosing process faults using neural network models
Energy Technology Data Exchange (ETDEWEB)
Buescher, K.L.; Jones, R.D.; Messina, M.J.
1993-11-01
In order to be of use for realistic problems, a fault diagnosis method should have the following three features. First, it should apply to nonlinear processes. Second, it should not rely on extensive amounts of data regarding previous faults. Lastly, it should detect faults promptly. The authors present such a scheme for static (i.e., non-dynamic) systems. It involves using a neural network to create an associative memory whose fixed points represent the normal behavior of the system.
Artificial Neural Networks in Stellar Astronomy
Directory of Open Access Journals (Sweden)
R. K. Gulati
2001-01-01
Full Text Available Next generation of optical spectroscopic surveys, such as the Sloan Digital Sky Survey and the 2 degree field survey, will provide large stellar databases. New tools will be required to extract useful information from these. We show the applications of artificial neural networks to stellar databases. In another application of this method, we predict spectral and luminosity classes from the catalog of spectral indices. We assess the importance of such methods for stellar populations studies.
Neural Networks with Complex and Quaternion Inputs
Rishiyur, Adityan
2006-01-01
This article investigates Kak neural networks, which can be instantaneously trained, for complex and quaternion inputs. The performance of the basic algorithm has been analyzed and shown how it provides a plausible model of human perception and understanding of images. The motivation for studying quaternion inputs is their use in representing spatial rotations that find applications in computer graphics, robotics, global navigation, computer vision and the spatial orientation of instruments. ...
Adaptive Filtering Using Recurrent Neural Networks
Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.
2005-01-01
A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.
Neural Networks in Chemical Reaction Dynamics
Raff, Lionel; Hagan, Martin
2011-01-01
This monograph presents recent advances in neural network (NN) approaches and applications to chemical reaction dynamics. Topics covered include: (i) the development of ab initio potential-energy surfaces (PES) for complex multichannel systems using modified novelty sampling and feedforward NNs; (ii) methods for sampling the configuration space of critical importance, such as trajectory and novelty sampling methods and gradient fitting methods; (iii) parametrization of interatomic potential functions using a genetic algorithm accelerated with a NN; (iv) parametrization of analytic interatomic
A Bionic Neural Network for Fish-Robot Locomotion
Institute of Scientific and Technical Information of China (English)
Dai-bing Zhang; De-wen Hu; Lin-cheng Shen; Hai-bin Xie
2006-01-01
A bionic neural network for fish-robot locomotion is presented. The bionic neural network inspired from fish neural network consists of one high level controller and one chain of central pattern generators (CPGs). Each CPG contains a nonlinear neural Zhang oscillator which shows properties similar to sine-cosine model. Simulation results show that the bionic neural network presents a good performance in controlling the fish-robot to execute various motions such as startup,stop,forward swimming,backward swimming,turn right and turn left.
Multilingual Text Detection with Nonlinear Neural Network
Directory of Open Access Journals (Sweden)
Lin Li
2015-01-01
Full Text Available Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work.
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... useful in the planning and maintenance of marine activities. Wave hindcasting is a non-real time application of numerical wave models in the broad field of climatology. Just as weather conditions, w ij weight from neuron j to neuron i YM Young’s model h a...
Deep learning in neural networks: an overview.
Schmidhuber, Jürgen
2015-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Yang, Yuning; Boling, Sam; Mason, Andrew J
2017-08-01
Next-generation brain machine interfaces demand a high-channel-count neural recording system to wirelessly monitor activities of thousands of neurons. A hardware efficient neural signal processor (NSP) is greatly desirable to ease the data bandwidth bottleneck for a fully implantable wireless neural recording system. This paper demonstrates a complete multichannel spike sorting NSP module that incorporates all of the necessary spike detector, feature extractor, and spike classifier blocks. To meet high-channel-count and implantability demands, each block was designed to be highly hardware efficient and scalable while sharing resources efficiently among multiple channels. To process multiple channels in parallel, scalability analysis was performed, and the utilization of each block was optimized according to its input data statistics and the power, area and/or speed of each block. Based on this analysis, a prototype 32-channel spike sorting NSP scalable module was designed and tested on an FPGA using synthesized datasets over a wide range of signal to noise ratios. The design was mapped to 130 nm CMOS to achieve 0.75 μW power and 0.023 mm(2) area consumptions per channel based on post synthesis simulation results, which permits scalability of digital processing to 690 channels on a 4×4 mm(2) electrode array.
Rule Extraction Algorithm for Deep Neural Networks: A Review
Hailesilassie, Tameru
2016-01-01
Despite the highest classification accuracy in wide varieties of application areas, artificial neural network has one disadvantage. The way this Network comes to a decision is not easily comprehensible. The lack of explanation ability reduces the acceptability of neural network in data mining and decision system. This drawback is the reason why researchers have proposed many rule extraction algorithms to solve the problem. Recently, Deep Neural Network (DNN) is achieving a profound result ove...
Classification of Respiratory Sounds by Using An Artificial Neural Network
2007-11-02
CLASSIFICATION OF RESPIRATORY SOUNDS BY USING AN ARTIFICIAL NEURAL NETWORK M.C. Sezgin, Z. Dokur, T. Ölmez, M. Korürek Department of Electronics and...successfully classified by the GAL network. Keywords-Respiratory Sounds, Classification of Biomedical Signals, Artificial Neural Network . I. INTRODUCTION...process, feature extraction, and classification by the artificial neural network . At first, the RS signal obtained from a real-time measurement equipment is
Functional model of biological neural networks.
Lo, James Ting-Ho
2010-12-01
A functional model of biological neural networks, called temporal hierarchical probabilistic associative memory (THPAM), is proposed in this paper. THPAM comprises functional models of dendritic trees for encoding inputs to neurons, a first type of neuron for generating spike trains, a second type of neuron for generating graded signals to modulate neurons of the first type, supervised and unsupervised Hebbian learning mechanisms for easy learning and retrieving, an arrangement of dendritic trees for maximizing generalization, hardwiring for rotation-translation-scaling invariance, and feedback connections with different delay durations for neurons to make full use of present and past informations generated by neurons in the same and higher layers. These functional models and their processing operations have many functions of biological neural networks that have not been achieved by other models in the open literature and provide logically coherent answers to many long-standing neuroscientific questions. However, biological justifications of these functional models and their processing operations are required for THPAM to qualify as a macroscopic model (or low-order approximate) of biological neural networks.
File access prediction using neural networks.
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.
Neural Network Approach for Eye Detection
Vijayalaxmi,; Sreehari, S
2012-01-01
Driving support systems, such as car navigation systems are becoming common and they support driver in several aspects. Non-intrusive method of detecting Fatigue and drowsiness based on eye-blink count and eye directed instruction controlhelps the driver to prevent from collision caused by drowsy driving. Eye detection and tracking under various conditions such as illumination, background, face alignment and facial expression makes the problem complex.Neural Network based algorithm is proposed in this paper to detect the eyes efficiently. In the proposed algorithm, first the neural Network is trained to reject the non-eye regionbased on images with features of eyes and the images with features of non-eye using Gabor filter and Support Vector Machines to reduce the dimension and classify efficiently. In the algorithm, first the face is segmented using L*a*btransform color space, then eyes are detected using HSV and Neural Network approach. The algorithm is tested on nearly 100 images of different persons under...
Artificial Neural Network Model for Predicting Compressive
Directory of Open Access Journals (Sweden)
Salim T. Yousif
2013-05-01
Full Text Available Compressive strength of concrete is a commonly used criterion in evaluating concrete. Although testing of the compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. Therefore, strength estimation of concrete at early time is highly desirable. This study presents the effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions, maximum aggregate size (MAS, and slump of fresh concrete. Back-propagation neural networks model is successively developed, trained, and tested using actual data sets of concrete mix proportions gathered from literature. The test of the model by un-used data within the range of input parameters shows that the maximum absolute error for model is about 20% and 88% of the output results has absolute errors less than 10%. The parametric study shows that water/cement ratio (w/c is the most significant factor affecting the output of the model. The results showed that neural networks has strong potential as a feasible tool for predicting compressive strength of concrete.
Phase Transitions in Living Neural Networks
Williams-Garcia, Rashid Vladimir
Our nervous systems are composed of intricate webs of interconnected neurons interacting in complex ways. These complex interactions result in a wide range of collective behaviors with implications for features of brain function, e.g., information processing. Under certain conditions, such interactions can drive neural network dynamics towards critical phase transitions, where power-law scaling is conjectured to allow optimal behavior. Recent experimental evidence is consistent with this idea and it seems plausible that healthy neural networks would tend towards optimality. This hypothesis, however, is based on two problematic assumptions, which I describe and for which I present alternatives in this thesis. First, critical transitions may vanish due to the influence of an environment, e.g., a sensory stimulus, and so living neural networks may be incapable of achieving "critical" optimality. I develop a framework known as quasicriticality, in which a relative optimality can be achieved depending on the strength of the environmental influence. Second, the power-law scaling supporting this hypothesis is based on statistical analysis of cascades of activity known as neuronal avalanches, which conflate causal and non-causal activity, thus confounding important dynamical information. In this thesis, I present a new method to unveil causal links, known as causal webs, between neuronal activations, thus allowing for experimental tests of the quasicriticality hypothesis and other practical applications.
CALIBRATION OF ONLINE ANALYZERS USING NEURAL NETWORKS
Energy Technology Data Exchange (ETDEWEB)
Rajive Ganguli; Daniel E. Walsh; Shaohai Yu
2003-12-05
Neural networks were used to calibrate an online ash analyzer at the Usibelli Coal Mine, Healy, Alaska, by relating the Americium and Cesium counts to the ash content. A total of 104 samples were collected from the mine, with 47 being from screened coal, and the rest being from unscreened coal. Each sample corresponded to 20 seconds of coal on the running conveyor belt. Neural network modeling used the quick stop training procedure. Therefore, the samples were split into training, calibration and prediction subsets. Special techniques, using genetic algorithms, were developed to representatively split the sample into the three subsets. Two separate approaches were tried. In one approach, the screened and unscreened coal was modeled separately. In another, a single model was developed for the entire dataset. No advantage was seen from modeling the two subsets separately. The neural network method performed very well on average but not individually, i.e. though each prediction was unreliable, the average of a few predictions was close to the true average. Thus, the method demonstrated that the analyzers were accurate at 2-3 minutes intervals (average of 6-9 samples), but not at 20 seconds (each prediction).
Identifying Broadband Rotational Spectra with Neural Networks
Zaleski, Daniel P.; Prozument, Kirill
2017-06-01
A typical broadband rotational spectrum may contain several thousand observable transitions, spanning many species. Identifying the individual spectra, particularly when the dynamic range reaches 1,000:1 or even 10,000:1, can be challenging. One approach is to apply automated fitting routines. In this approach, combinations of 3 transitions can be created to form a "triple", which allows fitting of the A, B, and C rotational constants in a Watson-type Hamiltonian. On a standard desktop computer, with a target molecule of interest, a typical AUTOFIT routine takes 2-12 hours depending on the spectral density. A new approach is to utilize machine learning to train a computer to recognize the patterns (frequency spacing and relative intensities) inherit in rotational spectra and to identify the individual spectra in a raw broadband rotational spectrum. Here, recurrent neural networks have been trained to identify different types of rotational spectra and classify them accordingly. Furthermore, early results in applying convolutional neural networks for spectral object recognition in broadband rotational spectra appear promising. Perez et al. "Broadband Fourier transform rotational spectroscopy for structure determination: The water heptamer." Chem. Phys. Lett., 2013, 571, 1-15. Seifert et al. "AUTOFIT, an Automated Fitting Tool for Broadband Rotational Spectra, and Applications to 1-Hexanal." J. Mol. Spectrosc., 2015, 312, 13-21. Bishop. "Neural networks for pattern recognition." Oxford university press, 1995.
Neural network parameters affecting image classification
Directory of Open Access Journals (Sweden)
K.C. Tiwari
2001-07-01
Full Text Available The study is to assess the behaviour and impact of various neural network parameters and their effects on the classification accuracy of remotely sensed images which resulted in successful classification of an IRS-1B LISS II image of Roorkee and its surrounding areas using neural network classification techniques. The method can be applied for various defence applications, such as for the identification of enemy troop concentrations and in logistical planning in deserts by identification of suitable areas for vehicular movement. Five parameters, namely training sample size, number of hidden layers, number of hidden nodes, learning rate and momentum factor were selected. In each case, sets of values were decided based on earlier works reported. Neural network-based classifications were carried out for as many as 450 combinations of these parameters. Finally, a graphical analysis of the results obtained was carried out to understand the relationship among these parameters. A table of recommended values for these parameters for achieving 90 per cent and higher classification accuracy was generated and used in classification of an IRS-1B LISS II image. The analysis suggests the existence of an intricate relationship among these parameters and calls for a wider series of classification experiments as also a more intricate analysis of the relationships.
Markovian architectural bias of recurrent neural networks.
Tino, Peter; Cernanský, Michal; Benusková, Lubica
2004-01-01
In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent neural networks (RNNs) reflects meaningful information processing states even prior to training [1], [2]. By concentrating on activation clusters in RNNs, while not throwing away the continuous state space network dynamics, we extract predictive models that we call neural prediction machines (NPMs). When RNNs with sigmoid activation functions are initialized with small weights (a common technique in the RNN community), the clusters of recurrent activations emerging prior to training are indeed meaningful and correspond to Markov prediction contexts. In this case, the extracted NPMs correspond to a class of Markov models, called variable memory length Markov models (VLMMs). In order to appreciate how much information has really been induced during the training, the RNN performance should always be compared with that of VLMMs and NPMs extracted before training as the "null" base models. Our arguments are supported by experiments on a chaotic symbolic sequence and a context-free language with a deep recursive structure. Index Terms-Complex symbolic sequences, information latching problem, iterative function systems, Markov models, recurrent neural networks (RNNs).
Artificial neural network applications in ionospheric studies
Directory of Open Access Journals (Sweden)
L. R. Cander
1998-06-01
Full Text Available The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC. Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.
Improved Extension Neural Network and Its Applications
Directory of Open Access Journals (Sweden)
Yu Zhou
2014-01-01
Full Text Available Extension neural network (ENN is a new neural network that is a combination of extension theory and artificial neural network (ANN. The learning algorithm of ENN is based on supervised learning algorithm. One of important issues in the field of classification and recognition of ENN is how to achieve the best possible classifier with a small number of labeled training data. Training data selection is an effective approach to solve this issue. In this work, in order to improve the supervised learning performance and expand the engineering application range of ENN, we use a novel data selection method based on shadowed sets to refine the training data set of ENN. Firstly, we use clustering algorithm to label the data and induce shadowed sets. Then, in the framework of shadowed sets, the samples located around each cluster centers (core data and the borders between clusters (boundary data are selected as training data. Lastly, we use selected data to train ENN. Compared with traditional ENN, the proposed improved ENN (IENN has a better performance. Moreover, IENN is independent of the supervised learning algorithms and initial labeled data. Experimental results verify the effectiveness and applicability of our proposed work.
Botwicz, Jakub; Buciak, Piotr; Sapiecha, Piotr
2006-03-01
Intrusion Prevention Systems (IPSs) have become widely recognized as a powerful tool and an important element of IT security safeguards. The essential feature of network IPSs is searching through network packets and matching multiple strings, that are fingerprints of known attacks. String matching is highly resource consuming and also the most significant bottleneck of IPSs. In this article an extension of the classical Karp-Rabin algorithm and its implementation architectures were examined. The result is a software, which generates a source code of a string matching module in hardware description language, that could be easily used to create an Intrusion Prevention System implemented in reconfigurable hardware. The prepared module matches the complete set of Snort IPS signatures achieving throughput of over 2 Gbps on an Altera Stratix I1 evaluation board. The most significant advantage of the proposed architecture is that the update of the patterns database does not require reconfiguration of the circuitry.
Locating hardware faults in a data communications network of a parallel computer
Archer, Charles J.; Megerian, Mark G.; Ratterman, Joseph D.; Smith, Brian E.
2010-01-12
Hardware faults location in a data communications network of a parallel computer. Such a parallel computer includes a plurality of compute nodes and a data communications network that couples the compute nodes for data communications and organizes the compute node as a tree. Locating hardware faults includes identifying a next compute node as a parent node and a root of a parent test tree, identifying for each child compute node of the parent node a child test tree having the child compute node as root, running a same test suite on the parent test tree and each child test tree, and identifying the parent compute node as having a defective link connected from the parent compute node to a child compute node if the test suite fails on the parent test tree and succeeds on all the child test trees.
A new approach to artificial neural networks.
Baptista Filho, B D; Cabral, E L; Soares, A J
1998-01-01
A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model with multiple synapses. The synapses' connective strengths are modified through selective and cumulative processes conducted by axo-axonic connections from a feedforward circuit. This new concept was applied to the position control of a planar two-link manipulator exhibiting excellent results on learning capability and generalization when compared with a conventional feedforward network. In the present paper, the example shows only a network developed from a neuronal reflexive circuit with some useful artifices, nevertheless without the intention of covering all possibilities devised.
Microscopic instability in recurrent neural networks
Yamanaka, Yuzuru; Amari, Shun-ichi; Shinomoto, Shigeru
2015-03-01
In a manner similar to the molecular chaos that underlies the stable thermodynamics of gases, a neuronal system may exhibit microscopic instability in individual neuronal dynamics while a macroscopic order of the entire population possibly remains stable. In this study, we analyze the microscopic stability of a network of neurons whose macroscopic activity obeys stable dynamics, expressing either monostable, bistable, or periodic state. We reveal that the network exhibits a variety of dynamical states for microscopic instability residing in a given stable macroscopic dynamics. The presence of a variety of dynamical states in such a simple random network implies more abundant microscopic fluctuations in real neural networks which consist of more complex and hierarchically structured interactions.
Neural networks optimally trained with noisy data
Wong, K. Y. Michael; Sherrington, David
1993-06-01
We study the retrieval behaviors of neural networks which are trained to optimize their performance for an ensemble of noisy example patterns. In particular, we consider (1) the performance overlap, which reflects the performance of the network in an operating condition identical to the training condition; (2) the storage overlap, which reflects the ability of the network to merely memorize the stored information; (3) the attractor overlap, which reflects the precision of retrieval for dilute feedback networks; and (4) the boundary overlap, which defines the boundary of the basin of attraction, and hence the associative ability for dilute feedback networks. We find that for sufficiently low training noise, the network optimizes its overall performance by sacrificing the individual performance of a minority of patterns, resulting in a two-band distribution of the aligning fields. For a narrow range of storage level, the network loses and then regains its retrieval capability when the training noise level increases, and we interpret that this reentrant retrieval behavior is related to competing tendencies in structuring the basins of attraction for the stored patterns. Reentrant behavior is also observed in the space of synaptic interactions, in which the replica symmetric solution of the optimal network destabilizes and then restabilizes when the training noise level increases. We summarize these observations by picturing training noises as an instrument for widening the basins of attractions of the stored patterns at the expense of reducing the precision of retrieval.
Fuzzy Neural Network Based Traffic Prediction and Congestion Control in High-Speed Networks
Institute of Scientific and Technical Information of China (English)
费翔; 何小燕; 罗军舟; 吴介一; 顾冠群
2000-01-01
Congestion control is one of the key problems in high-speed networks, such as ATM. In this paper, a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach. Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error. Fuzzy neural network developed in this paper can solve these problems satisfactorily. Simulations show the comparison among no-feedback control scheme,reactive control scheme and neural network based control scheme.
Models of neural networks with fuzzy activation functions
Nguyen, A. T.; Korikov, A. M.
2017-02-01
This paper investigates the application of a new form of neuron activation functions that are based on the fuzzy membership functions derived from the theory of fuzzy systems. On the basis of the results regarding neuron models with fuzzy activation functions, we created the models of fuzzy-neural networks. These fuzzy-neural network models differ from conventional networks that employ the fuzzy inference systems using the methods of neural networks. While conventional fuzzy-neural networks belong to the first type, fuzzy-neural networks proposed here are defined as the second-type models. The simulation results show that the proposed second-type model can successfully solve the problem of the property prediction for time – dependent signals. Neural networks with fuzzy impulse activation functions can be widely applied in many fields of science, technology and mechanical engineering to solve the problems of classification, prediction, approximation, etc.
Time Series Prediction based on Hybrid Neural Networks
Directory of Open Access Journals (Sweden)
S. A. Yarushev
2016-01-01
Full Text Available In this paper, we suggest to use hybrid approach to time series forecasting problem. In first part of paper, we create a literature review of time series forecasting methods based on hybrid neural networks and neuro-fuzzy approaches. Hybrid neural networks especially effective for specific types of applications such as forecasting or classification problem, in contrast to traditional monolithic neural networks. These classes of problems include problems with different characteristics in different modules. The main part of paper create a detailed overview of hybrid networks benefits, its architectures and performance under traditional neural networks. Hybrid neural networks models for time series forecasting are discussed in the paper. Experiments with modular neural networks are given.
PSO optimized Feed Forward Neural Network for offline Signature Classification
Directory of Open Access Journals (Sweden)
Pratik R. Hajare
2015-07-01
Full Text Available The paper is based on feed forward neural network (FFNN optimization by particle swarm intelligence (PSI used to provide initial weights and biases to train neural network. Once the weights and biases are found using Particle swarm optimization (PSO with neural network used as training algorithm for specified epoch, the same are used to train the neural network for training and classification of benchmark problems. Further the approach is tested for offline signature classifications. A comparison is made between normal FFNN with random weights and biases and FFNN with particle swarm optimized weights and biases. Firstly, the performance is tested on two benchmark databases for neural network, The Breast Cancer Database and the Diabetic Database. Result shows that neural network performs better with initial weights and biases obtained by Particle Swarm optimization. The network converges faster with PSO obtained initial weights and biases for FFNN and classification accuracy is increased.
Runoff Modelling in Urban Storm Drainage by Neural Networks
DEFF Research Database (Denmark)
Rasmussen, Michael R.; Brorsen, Michael; Schaarup-Jensen, Kjeld
1995-01-01
network is used to compute flow or water level at selected points in the sewer system, and to forecast the flow from a small residential area. The main advantages of the neural network are the build-in self calibration procedure and high speed performance, but the neural network cannot be used to extract......A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural...... knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model....
Detection of Wildfires with Artificial Neural Networks
Umphlett, B.; Leeman, J.; Morrissey, M. L.
2011-12-01
Currently fire detection for the National Oceanic and Atmospheric Administration (NOAA) using satellite data is accomplished with algorithms and error checking human analysts. Artificial neural networks (ANNs) have been shown to be more accurate than algorithms or statistical methods for applications dealing with multiple datasets of complex observed data in the natural sciences. ANNs also deal well with multiple data sources that are not all equally reliable or equally informative to the problem. An ANN was tested to evaluate its accuracy in detecting wildfires utilizing polar orbiter numerical data from the Advanced Very High Resolution Radiometer (AVHRR). Datasets containing locations of known fires were gathered from the NOAA's polar orbiting satellites via the Comprehensive Large Array-data Stewardship System (CLASS). The data was then calibrated and navigation corrected using the Environment for Visualizing Images (ENVI). Fires were located with the aid of shapefiles generated via ArcGIS. Afterwards, several smaller ten pixel by ten pixel datasets were created for each fire (using the ENVI corrected data). Several datasets were created for each fire in order to vary fire position and avoid training the ANN to look only at fires in the center of an image. Datasets containing no fires were also created. A basic pattern recognition neural network was established with the MATLAB neural network toolbox. The datasets were then randomly separated into categories used to train, validate, and test the ANN. To prevent over fitting of the data, the mean squared error (MSE) of the network was monitored and training was stopped when the MSE began to rise. Networks were tested using each channel of the AVHRR data independently, channels 3a and 3b combined, and all six channels. The number of hidden neurons for each input set was also varied between 5-350 in steps of 5 neurons. Each configuration was run 10 times, totaling about 4,200 individual network evaluations. Thirty
Phase Synchronization in Small World Chaotic Neural Networks
Institute of Scientific and Technical Information of China (English)
WANG Qing-Yun; LU Qi-Shao
2005-01-01
@@ To understand collective motion of realneural networks very well, we investigate collective phase synchronization of small world chaotic Hindmarsh-Rose (HR) neural networks. By numerical simulations, we conclude that small world chaotic HR neural networks can achieve collective phase synchronization. Furthermore, it is shown that phase synchronization of small world chaotic HR neural networks is dependent on the coupling strength,the connection topology (which is determined by the probability p), as well as the coupling number. These phenomena are important to guide us to understand the synchronization of real neural networks.
Network traffic anomaly prediction using Artificial Neural Network
Ciptaningtyas, Hening Titi; Fatichah, Chastine; Sabila, Altea
2017-03-01
As the excessive increase of internet usage, the malicious software (malware) has also increase significantly. Malware is software developed by hacker for illegal purpose(s), such as stealing data and identity, causing computer damage, or denying service to other user[1]. Malware which attack computer or server often triggers network traffic anomaly phenomena. Based on Sophos's report[2], Indonesia is the riskiest country of malware attack and it also has high network traffic anomaly. This research uses Artificial Neural Network (ANN) to predict network traffic anomaly based on malware attack in Indonesia which is recorded by Id-SIRTII/CC (Indonesia Security Incident Response Team on Internet Infrastructure/Coordination Center). The case study is the highest malware attack (SQL injection) which has happened in three consecutive years: 2012, 2013, and 2014[4]. The data series is preprocessed first, then the network traffic anomaly is predicted using Artificial Neural Network and using two weight update algorithms: Gradient Descent and Momentum. Error of prediction is calculated using Mean Squared Error (MSE) [7]. The experimental result shows that MSE for SQL Injection is 0.03856. So, this approach can be used to predict network traffic anomaly.
IT Career JumpStart An Introduction to PC Hardware, Software, and Networking
Alpern, Naomi J; Muller, Randy
2011-01-01
A practical approach for anyone looking to enter the IT workforce Before candidates can begin to prepare for any kind of certification, they need a basic understanding of the various hardware and software components used in a computer network. Aimed at aspiring IT professionals, this invaluable book strips down a network to its bare basics, and discusses this complex topic in a clear and concise manner so that IT beginners can confidently gain an understanding of fundamental IT concepts. In addition, a base knowledge has been established so that more advanced topics and technologies can be lea
Brain tumor segmentation with Deep Neural Networks.
Havaei, Mohammad; Davy, Axel; Warde-Farley, David; Biard, Antoine; Courville, Aaron; Bengio, Yoshua; Pal, Chris; Jodoin, Pierre-Marc; Larochelle, Hugo
2017-01-01
In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster.
Sparse coding for layered neural networks
Katayama, Katsuki; Sakata, Yasuo; Horiguchi, Tsuyoshi
2002-07-01
We investigate storage capacity of two types of fully connected layered neural networks with sparse coding when binary patterns are embedded into the networks by a Hebbian learning rule. One of them is a layered network, in which a transfer function of even layers is different from that of odd layers. The other is a layered network with intra-layer connections, in which the transfer function of inter-layer is different from that of intra-layer, and inter-layered neurons and intra-layered neurons are updated alternately. We derive recursion relations for order parameters by means of the signal-to-noise ratio method, and then apply the self-control threshold method proposed by Dominguez and Bollé to both layered networks with monotonic transfer functions. We find that a critical value αC of storage capacity is about 0.11|a ln a| -1 ( a≪1) for both layered networks, where a is a neuronal activity. It turns out that the basin of attraction is larger for both layered networks when the self-control threshold method is applied.
The effect of the neural activity on topological properties of growing neural networks.
Gafarov, F M; Gafarova, V R
2016-09-01
The connectivity structure in cortical networks defines how information is transmitted and processed, and it is a source of the complex spatiotemporal patterns of network's development, and the process of creation and deletion of connections is continuous in the whole life of the organism. In this paper, we study how neural activity influences the growth process in neural networks. By using a two-dimensional activity-dependent growth model we demonstrated the neural network growth process from disconnected neurons to fully connected networks. For making quantitative investigation of the network's activity influence on its topological properties we compared it with the random growth network not depending on network's activity. By using the random graphs theory methods for the analysis of the network's connections structure it is shown that the growth in neural networks results in the formation of a well-known "small-world" network.
Current-mode implementation of processing modules in ART-based neural networks
Lopez-Alcantud, Jose-Alejandro; Hauer, Hans; Diaz-Madrid, Jose-Angel; Ruiz-Merino, Ramon
2003-04-01
This paper describes implementation of neural network processing layers using basic current-mode operating modules. The research work has been focused on the implementation of neural networks based on the Adaptive Resonance Theory, developed by S. Grossberg and G.A. Carpenter. The ART-based neural network whose operating modules have been choosen for development is the one called MART, proposed by F. Delgado, because of its complex architecture, auto--adaptive self-learning process, able to discard unmeaningful cathegories. Our presentation starts introducing the behaviour of MART with an analysis of its structure. The development described by this research work is focused on the monochannel block included in the main signal processing part of the MART neural network. The description of the computing algorithm of the layers inside a monochannel block are also provided in order to show what operational current-mode modules are needed (multiplier, divider, square-rooter, adder, substractor, absolute value, maximum and minimum evaluator...). Descriptions at schematic and layout levels of all the processing layers are given. All of them have been designed using AMS 0.35 micron technology with a supply voltage of 3.3 volts. The modules are designed to deal with input currents in the range of 20 to 50 microamps, showing a lineal behaviour and an output error of less than 10%, which is good enough for neural signal processing systems. The maximum frecuency of operation is around 200 kHz. Simulation results are included to show that the operation performed by the hardware designed matches the behaviour described by the MART neural network. For testing purposes we show the design of a monochannel block hardware implementation restricted to five inputs and three cathegories.
Granular neural networks, pattern recognition and bioinformatics
Pal, Sankar K; Ganivada, Avatharam
2017-01-01
This book provides a uniform framework describing how fuzzy rough granular neural network technologies can be formulated and used in building efficient pattern recognition and mining models. It also discusses the formation of granules in the notion of both fuzzy and rough sets. Judicious integration in forming fuzzy-rough information granules based on lower approximate regions enables the network to determine the exactness in class shape as well as to handle the uncertainties arising from overlapping regions, resulting in efficient and speedy learning with enhanced performance. Layered network and self-organizing analysis maps, which have a strong potential in big data, are considered as basic modules,. The book is structured according to the major phases of a pattern recognition system (e.g., classification, clustering, and feature selection) with a balanced mixture of theory, algorithm, and application. It covers the latest findings as well as directions for future research, particularly highlighting bioinf...
Dynamic artificial neural networks with affective systems.
Schuman, Catherine D; Birdwell, J Douglas
2013-01-01
Artificial neural networks (ANNs) are processors that are trained to perform particular tasks. We couple a computational ANN with a simulated affective system in order to explore the interaction between the two. In particular, we design a simple affective system that adjusts the threshold values in the neurons of our ANN. The aim of this paper is to demonstrate that this simple affective system can control the firing rate of the ensemble of neurons in the ANN, as well as to explore the coupling between the affective system and the processes of long term potentiation (LTP) and long term depression (LTD), and the effect of the parameters of the affective system on its performance. We apply our networks with affective systems to a simple pole balancing example and briefly discuss the effect of affective systems on network performance.
Flood routing modelling with Artificial Neural Networks
Directory of Open Access Journals (Sweden)
R. Peters
2006-01-01
Full Text Available For the modelling of the flood routing in the lower reaches of the Freiberger Mulde river and its tributaries the one-dimensional hydrodynamic modelling system HEC-RAS has been applied. Furthermore, this model was used to generate a database to train multilayer feedforward networks. To guarantee numerical stability for the hydrodynamic modelling of some 60 km of streamcourse an adequate resolution in space requires very small calculation time steps, which are some two orders of magnitude smaller than the input data resolution. This leads to quite high computation requirements seriously restricting the application – especially when dealing with real time operations such as online flood forecasting. In order to solve this problem we tested the application of Artificial Neural Networks (ANN. First studies show the ability of adequately trained multilayer feedforward networks (MLFN to reproduce the model performance.
Stability of discrete Hopfield neural networks with delay
Institute of Scientific and Technical Information of China (English)
Ma Runnian; Lei Sheping; Liu Naigong
2005-01-01
Discrete Hopfield neural network with delay is an extension of discrete Hopfield neural network. As it is well known, the stability of neural networks is not only the most basic and important problem but also foundation of the network's applications. The stability of discrete Hopfield neural networks with delay is mainly investigated by using Lyapunov function. The sufficient conditions for the networks with delay converging towards a limit cycle of length 4 are obtained. Also, some sufficient criteria are given to ensure the networks having neither a stable state nor a limit cycle with length 2. The obtained results here generalize the previous results on stability of discrete Hopfield neural network with delay and without delay.
Advances in Artificial Neural Networks - Methodological Development and Application
Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...
An evolutionary approach to associative memory in recurrent neural networks
Fujita, Sh; Fujita, Sh; Nishimura, H
1994-01-01
Abstract: In this paper, we investigate the associative memory in recurrent neural networks, based on the model of evolving neural networks proposed by Nolfi, Miglino and Parisi. Experimentally developed network has highly asymmetric synaptic weights and dilute connections, quite different from those of the Hopfield model. Some results on the effect of learning efficiency on the evolution are also presented.
Solving quadratic programming problems by delayed projection neural network.
Yang, Yongqing; Cao, Jinde
2006-11-01
In this letter, the delayed projection neural network for solving convex quadratic programming problems is proposed. The neural network is proved to be globally exponentially stable and can converge to an optimal solution of the optimization problem. Three examples show the effectiveness of the proposed network.
The Projection Neural Network for Solving Convex Nonlinear Programming
Yang, Yongqing; Xu, Xianyun
In this paper, a projection neural network for solving convex optimization is investigated. Using Lyapunov stability theory and LaSalle invariance principle, the proposed network is showed to be globally stable and converge to exact optimal solution. Two examples show the effectiveness of the proposed neural network model.
Prediction of Parametric Roll Resonance by Multilayer Perceptron Neural Network
DEFF Research Database (Denmark)
Míguez González, M; López Peña, F.; Díaz Casás, V.
2011-01-01
acknowledged in the last few years. This work proposes a prediction system based on a multilayer perceptron (MP) neural network. The training and testing of the MP network is accomplished by feeding it with simulated data of a three degrees-of-freedom nonlinear model of a fishing vessel. The neural network...
Prediction of Parametric Roll Resonance by Multilayer Perceptron Neural Network
DEFF Research Database (Denmark)
Míguez González, M; López Peña, F.; Díaz Casás, V.
2011-01-01
acknowledged in the last few years. This work proposes a prediction system based on a multilayer perceptron (MP) neural network. The training and testing of the MP network is accomplished by feeding it with simulated data of a three degrees-of-freedom nonlinear model of a fishing vessel. The neural network...
Neural network model to control an experimental chaotic pendulum
Bakker, R; Schouten, JC; Takens, F; vandenBleek, CM
1996-01-01
A feedforward neural network was trained to predict the motion of an experimental, driven, and damped pendulum operating in a chaotic regime. The network learned the behavior of the pendulum from a time series of the pendulum's angle, the single measured variable. The validity of the neural network,
Explicit neural representations, recursive neural networks and conscious visual perception.
Pollen, Daniel A
2003-08-01
The fundamental question as to whether the neural correlates of any given conscious visual experience are expressed locally within a given cortical area or more globally within some widely distributed network remains unresolved. We inquire as to whether recursive processing-by which we mean the combined flow and integrated outcome of afferent and recurrent activity across a series of cortical areas-is essential for the emergence of conscious visual experience. If so, we further inquire as to whether such recursive processing is essential only for loops between extrastriate cortical areas explicitly representing experiences such as color or motion back to V1 or whether it is processing between still higher levels and the areas computing such explicit representations that is exclusively or additionally essential for visual experience. If recursive processing is not essential for the emergence of conscious visual experience, then it should also be possible to determine whether it is only the intracortical sensory processing within areas computing explicit sensory representations that is required for perceptual experience or whether it is the subsequent processing of the output of such areas within more anterior cortical regions that engenders perception. The present analysis suggests that the questions posed here may ultimately become experimentally resolvable. Whatever the outcome, the results will likely open new approaches to identify the neural correlates of conscious visual perception.
Nonlinear system identification and control based on modular neural networks.
Puscasu, Gheorghe; Codres, Bogdan
2011-08-01
A new approach for nonlinear system identification and control based on modular neural networks (MNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This is obtained using a partitioning algorithm. Each local nonlinear model is associated with a nonlinear controller. These are also implemented by neural networks. The switching between the neural controllers is done by a dynamical switcher, also implemented by neural networks, that tracks the different operating points. The proposed multiple modelling and control strategy has been successfully tested on simulated laboratory scale liquid-level system.