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.
Character Recognition Using Genetically Trained Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.
1998-10-01
Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the
Adaptive training of feedforward neural networks by Kalman filtering
Energy Technology Data Exchange (ETDEWEB)
Ciftcioglu, Oe. [Istanbul Technical Univ. (Turkey). Dept. of Electrical Engineering; Tuerkcan, E. [Netherlands Energy Research Foundation (ECN), Petten (Netherlands)
1995-02-01
Adaptive training of feedforward neural networks by Kalman filtering is described. Adaptive training is particularly important in estimation by neural network in real-time environmental where the trained network is used for system estimation while the network is further trained by means of the information provided by the experienced/exercised ongoing operation. As result of this, neural network adapts itself to a changing environment to perform its mission without recourse to re-training. The performance of the training method is demonstrated by means of actual process signals from a nuclear power plant. (orig.).
Training product unit neural networks with genetic algorithms
Janson, D. J.; Frenzel, J. F.; Thelen, D. C.
1991-01-01
The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.
Behaviour in O of the Neural Networks Training Cost
DEFF Research Database (Denmark)
Goutte, Cyril
1998-01-01
We study the behaviour in zero of the derivatives of the cost function used when training non-linear neural networks. It is shown that a fair number offirst, second and higher order derivatives vanish in zero, validating the belief that 0 is a peculiar and potentially harmful location....... These calculations arerelated to practical and theoretical aspects of neural networks training....
Parallelization of Neural Network Training for NLP with Hogwild!
Directory of Open Access Journals (Sweden)
Deyringer Valentin
2017-10-01
Full Text Available Neural Networks are prevalent in todays NLP research. Despite their success for different tasks, training time is relatively long. We use Hogwild! to counteract this phenomenon and show that it is a suitable method to speed up training Neural Networks of different architectures and complexity. For POS tagging and translation we report considerable speedups of training, especially for the latter. We show that Hogwild! can be an important tool for training complex NLP architectures.
Recurrent neural networks training with stable bounding ellipsoid algorithm.
Yu, Wen; de Jesús Rubio, José
2009-06-01
Bounding ellipsoid (BE) algorithms offer an attractive alternative to traditional training algorithms for neural networks, for example, backpropagation and least squares methods. The benefits include high computational efficiency and fast convergence speed. In this paper, we propose an ellipsoid propagation algorithm to train the weights of recurrent neural networks for nonlinear systems identification. Both hidden layers and output layers can be updated. The stability of the BE algorithm is proven.
Unsupervised pre-training for fully convolutional neural networks
Wiehman, Stiaan; Kroon, Steve; Villiers, De Hendrik
2017-01-01
Unsupervised pre-Training of neural networks has been shown to act as a regularization technique, improving performance and reducing model variance. Recently, fully convolutional networks (FCNs) have shown state-of-The-Art results on various semantic segmentation tasks. Unfortunately, there is no
Neural network training as a dissipative process.
Gori, Marco; Maggini, Marco; Rossi, Alessandro
2016-09-01
This paper analyzes the practical issues and reports some results on a theory in which learning is modeled as a continuous temporal process driven by laws describing the interactions of intelligent agents with their own environment. The classic regularization framework is paired with the idea of temporal manifolds by introducing the principle of least cognitive action, which is inspired by the related principle of mechanics. The introduction of the counterparts of the kinetic and potential energy leads to an interpretation of learning as a dissipative process. As an example, we apply the theory to supervised learning in neural networks and show that the corresponding Euler-Lagrange differential equations can be connected to the classic gradient descent algorithm on the supervised pairs. We give preliminary experiments to confirm the soundness of the theory. Copyright © 2016 Elsevier Ltd. All rights reserved.
Bayesian model ensembling using meta-trained recurrent neural networks
Ambrogioni, L.; Berezutskaya, Y.; Gü ç lü , U.; Borne, E.W.P. van den; Gü ç lü tü rk, Y.; Gerven, M.A.J. van; Maris, E.G.G.
2017-01-01
In this paper we demonstrate that a recurrent neural network meta-trained on an ensemble of arbitrary classification tasks can be used as an approximation of the Bayes optimal classifier. This result is obtained by relying on the framework of e-free approximate Bayesian inference, where the Bayesian
Reformulated radial basis neural networks trained by gradient descent.
Karayiannis, N B
1999-01-01
This paper presents an axiomatic approach for constructing radial basis function (RBF) neural networks. This approach results in a broad variety of admissible RBF models, including those employing Gaussian RBF's. The form of the RBF's is determined by a generator function. New RBF models can be developed according to the proposed approach by selecting generator functions other than exponential ones, which lead to Gaussian RBF's. This paper also proposes a supervised learning algorithm based on gradient descent for training reformulated RBF neural networks constructed using the proposed approach. A sensitivity analysis of the proposed algorithm relates the properties of RBF's with the convergence of gradient descent learning. Experiments involving a variety of reformulated RBF networks generated by linear and exponential generator functions indicate that gradient descent learning is simple, easily implementable, and produces RBF networks that perform considerably better than conventional RBF models trained by existing algorithms.
Aplication of artificial neural network model in aviation specialist training
Directory of Open Access Journals (Sweden)
Висиль Миколайович Казак
2016-02-01
Full Text Available This paper reviews the application of artificial neural network (ANN model in aviation specialist training. The ANN model is based on the dependence of residual knowledge of subjects of study on their individual abilities. The residual knowledge is the skills acquired by the subject before he is going for an occupation. The presented ANN model gives the possibility to predict the level of professional training of the specialists with high accuracy
Training strategy for convolutional neural networks in pedestrian gender classification
Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min
2017-06-01
In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.
The extraction of information and knowledge from trained neural networks.
Livingstone, David J; Browne, Antony; Crichton, Raymond; Hudson, Brian D; Whitley, David C; Ford, Martyn G
2008-01-01
In the past, neural networks were viewed as classification and regression systems whose internal representations were incomprehensible. It is now becoming apparent that algorithms can be designed that extract comprehensible representations from trained neural networks, enabling them to be used for data mining and knowledge discovery, that is, the discovery and explanation of previously unknown relationships present in data. This chapter reviews existing algorithms for extracting comprehensible representations from neural networks and outlines research to generalize and extend the capabilities of one of these algorithms, TREPAN. This algorithm has been generalized for application to bioinformatics data sets, including the prediction of splice junctions in human DNA sequences, and cheminformatics. The results generated on these data sets are compared with those generated by a conventional data mining technique (C5) and appropriate conclusions are drawn.
Modelling electric trains energy consumption using Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Martinez Fernandez, P.; Garcia Roman, C.; Insa Franco, R.
2016-07-01
Nowadays there is an evident concern regarding the efficiency and sustainability of the transport sector due to both the threat of climate change and the current financial crisis. This concern explains the growth of railways over the last years as they present an inherent efficiency compared to other transport means. However, in order to further expand their role, it is necessary to optimise their energy consumption so as to increase their competitiveness. Improving railways energy efficiency requires both reliable data and modelling tools that will allow the study of different variables and alternatives. With this need in mind, this paper presents the development of consumption models based on neural networks that calculate the energy consumption of electric trains. These networks have been trained based on an extensive set of consumption data measured in line 1 of the Valencia Metro Network. Once trained, the neural networks provide a reliable estimation of the vehicles consumption along a specific route when fed with input data such as train speed, acceleration or track longitudinal slope. These networks represent a useful modelling tool that may allow a deeper study of railway lines in terms of energy expenditure with the objective of reducing the costs and environmental impact associated to railways. (Author)
Accelerating deep neural network training with inconsistent stochastic gradient descent.
Wang, Linnan; Yang, Yi; Min, Renqiang; Chakradhar, Srimat
2017-09-01
Stochastic Gradient Descent (SGD) updates Convolutional Neural Network (CNN) with a noisy gradient computed from a random batch, and each batch evenly updates the network once in an epoch. This model applies the same training effort to each batch, but it overlooks the fact that the gradient variance, induced by Sampling Bias and Intrinsic Image Difference, renders different training dynamics on batches. In this paper, we develop a new training strategy for SGD, referred to as Inconsistent Stochastic Gradient Descent (ISGD) to address this problem. The core concept of ISGD is the inconsistent training, which dynamically adjusts the training effort w.r.t the loss. ISGD models the training as a stochastic process that gradually reduces down the mean of batch's loss, and it utilizes a dynamic upper control limit to identify a large loss batch on the fly. ISGD stays on the identified batch to accelerate the training with additional gradient updates, and it also has a constraint to penalize drastic parameter changes. ISGD is straightforward, computationally efficient and without requiring auxiliary memories. A series of empirical evaluations on real world datasets and networks demonstrate the promising performance of inconsistent training. Copyright © 2017 Elsevier Ltd. All rights reserved.
Novel maximum-margin training algorithms for supervised neural networks.
Ludwig, Oswaldo; Nunes, Urbano
2010-06-01
This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by
Deep Convolutional Neural Networks: Structure, Feature Extraction and Training
Directory of Open Access Journals (Sweden)
Namatēvs Ivars
2017-12-01
Full Text Available Deep convolutional neural networks (CNNs are aimed at processing data that have a known network like topology. They are widely used to recognise objects in images and diagnose patterns in time series data as well as in sensor data classification. The aim of the paper is to present theoretical and practical aspects of deep CNNs in terms of convolution operation, typical layers and basic methods to be used for training and learning. Some practical applications are included for signal and image classification. Finally, the present paper describes the proposed block structure of CNN for classifying crucial features from 3D sensor data.
Training Feedforward Neural Networks Using Symbiotic Organisms Search Algorithm.
Wu, Haizhou; Zhou, Yongquan; Luo, Qifang; Basset, Mohamed Abdel
2016-01-01
Symbiotic organisms search (SOS) is a new robust and powerful metaheuristic algorithm, which stimulates the symbiotic interaction strategies adopted by organisms to survive and propagate in the ecosystem. In the supervised learning area, it is a challenging task to present a satisfactory and efficient training algorithm for feedforward neural networks (FNNs). In this paper, SOS is employed as a new method for training FNNs. To investigate the performance of the aforementioned method, eight different datasets selected from the UCI machine learning repository are employed for experiment and the results are compared among seven metaheuristic algorithms. The results show that SOS performs better than other algorithms for training FNNs in terms of converging speed. It is also proven that an FNN trained by the method of SOS has better accuracy than most algorithms compared.
Introduction to neural networks
James, Frederick E
1994-02-02
1. Introduction and overview of Artificial Neural Networks. 2,3. The Feed-forward Network as an inverse Problem, and results on the computational complexity of network training. 4.Physics applications of neural networks.
An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks.
Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen
2016-01-01
The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper.
Neural network for regression problems with reduced training sets.
Bataineh, Mohammad; Marler, Timothy
2017-11-01
Although they are powerful and successful in many applications, artificial neural networks (ANNs) typically do not perform well with complex problems that have a limited number of training cases. Often, collecting additional training data may not be feasible or may be costly. Thus, this work presents a new radial-basis network (RBN) design that overcomes the limitations of using ANNs to accurately model regression problems with minimal training data. This new design involves a multi-stage training process that couples an orthogonal least squares (OLS) technique with gradient-based optimization. New termination criteria are also introduced to improve accuracy. In addition, the algorithms are designed to require minimal heuristic parameters, thus improving ease of use and consistency in performance. The proposed approach is tested with experimental and practical regression problems, and the results are compared with those from typical network models. The results show that the new design demonstrates improved accuracy with reduced dependence on the amount of training data. As demonstrated, this new ANN provides a platform for approximating potentially slow but high-fidelity computational models, and thus fostering inter-model connectivity and multi-scale modeling. Copyright © 2017 Elsevier Ltd. All rights reserved.
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.
Purely sequence trained neural networks for ASR based on lattice free MMI (Author’s Manuscript)
2016-09-08
Purely sequence-trained neural networks for ASR based on lattice-free MMI Daniel Povey1,2, Vijayaditya Peddinti1, Daniel Galvez3, Pegah Ghahrmani1...we describe a method to perform sequence- discriminative training of neural network acoustic models with- out the need for frame-level cross-entropy... neural network outputs at one third the standard frame rate. These changes en- able us to perform the computation for the forward-backward algorithm
Fast training of neural networks for load forecasting
Energy Technology Data Exchange (ETDEWEB)
Agosta, J.M.; Nielsen, N.R.; Andeen, G. [SRI International, Menlo Park, CA (United States)
1996-10-01
Predicting load demand (e.g., demand for electric power) in a data-rich environment is basically a regression problem. To be successful, however, any regression technique must take into account the nonlinear nature of the problem. Numerous nonlinear regression methods have become practical, with the availability of more powerful computers. Perhaps the best known of these methods are techniques that have been popularized under the name of neural networks, and the most common of these is the back-propagation neural network (BPNN). This paper explains the advantage of a different nonlinear regression method known as the probabilistic neural network (PNN).
Distributed algorithm to train neural networks using the Map Reduce paradigm
Directory of Open Access Journals (Sweden)
Cristian Mihai BARCA
2017-07-01
Full Text Available With rapid development of powerful computer systems during past decade, parallel and distributed processing becomes a significant resource for fast neural network training, even for real-time processing. Different parallel computing based methods have been proposed in recent years for the development of system performance. The two main methods are to distribute the patterns that are used for training - training set level parallelism, or to distribute the computation performed by the neural network - neural network level parallelism. In the present research work we have focused on the first method.
Training Convolutional Neural Networks for Translational Invariance on SAR ATR
DEFF Research Database (Denmark)
Malmgren-Hansen, David; Engholm, Rasmus; Østergaard Pedersen, Morten
2016-01-01
In this paper we present a comparison of the robustness of Convolutional Neural Networks (CNN) to other classifiers in the presence of uncertainty of the objects localization in SAR image. We present a framework for simulating simple SAR images, translating the object of interest systematically...
Reinforcement and backpropagation training for an optical neural network using self-lensing effects.
Cruz-Cabrera, A A; Yang, M; Cui, G; Behrman, E C; Steck, J E; Skinner, S R
2000-01-01
The optical bench training of an optical feedforward neural network, developed by the authors, is presented. The network uses an optical nonlinear material for neuron processing and a trainable applied optical pattern as the network weights. The nonlinear material, with the applied weight pattern, modulates the phase front of a forward propagating information beam by dynamically altering the index of refraction profile of the material. To verify that the network can be trained in real time, six logic gates were trained using a reinforcement training paradigm. More importantly, to demonstrate optical backpropagation, three gates were trained via optical error backpropagation. The output error is optically backpropagated, detected with a CCD camera, and the weight pattern is updated and stored on a computer. The obtained results lay the ground work for the implementation of multilayer neural networks that are trained using optical error backpropagation and are able to solve more complex problems.
Internal-state analysis in layered artificial neural network trained to categorize lung sounds
Oud, M
2002-01-01
In regular use of artificial neural networks, only input and output states of the network are known to the user. Weight and bias values can be extracted but are difficult to interpret. We analyzed internal states of networks trained to map asthmatic lung sound spectra onto lung function parameters.
Non-Linear State Estimation Using Pre-Trained Neural Networks
DEFF Research Database (Denmark)
Bayramoglu, Enis; Andersen, Nils Axel; Ravn, Ole
2010-01-01
effecting the transformation. This function is approximated by a neural network using offline training. The training is based on monte carlo sampling. A way to obtain parametric distributions of flexible shape to be used easily with these networks is also presented. The method can also be used to improve...... other parametric methods around regions with strong non-linearities by including them inside the network....
Directory of Open Access Journals (Sweden)
Yi-Qing Wang
2015-09-01
Full Text Available Recent years have seen a surge of interest in multilayer neural networks fueled by their successful applications in numerous image processing and computer vision tasks. In this article, we describe a C++ implementation of the stochastic gradient descent to train a multilayer neural network, where a fast and accurate acceleration of tanh(· is achieved with linear interpolation. As an example of application, we present a neural network able to deliver state-of-the-art performance in image demosaicing.
Iizaka, Tatsuya; Matsui, Tetsuro; Fukuyama, Yoshikazu
This paper presents a daily peak load forecasting method using an analyzable structured neural network (ASNN) in order to explain forecasting reasons. In this paper, we propose a new training method for ASNN in order to explain forecasting reason more properly than the conventional training method. ASNN consists of two types of hidden units. One type of hidden units has connecting weights between the hidden units and only one group of related input units. Another one has connecting weights between the hidden units and all input units. The former type of hidden units allows to explain forecasting reasons. The latter type of hidden units ensures the forecasting performance. The proposed training method make the former type of hidden units train only independent relations between the input factors and output, and make the latter type of hidden units train only complicated interactions between input factors. The effectiveness of the proposed neural network is shown using actual daily peak load. ASNN trained by the proposed method can explain forecasting reasons more properly than ASNN trained by the conventional method. Moreover, the proposed neural network can forecast daily peak load more accurately than conventional neural network trained by the back propagation algorithm.
Multiobjective training of artificial neural networks for rainfall-runoff modeling
De Vos, N.J.; Rientjes, T.H.M.
2008-01-01
This paper presents results on the application of various optimization algorithms for the training of artificial neural network rainfall-runoff models. Multilayered feed-forward networks for forecasting discharge from two mesoscale catchments in different climatic regions have been developed for
An R implementation of a Recurrent Neural Network Trained by Extended Kalman Filter
Directory of Open Access Journals (Sweden)
Bogdan Oancea
2016-06-01
Full Text Available Nowadays there are several techniques used for forecasting with different performances and accuracies. One of the most performant techniques for time series prediction is neural networks. The accuracy of the predictions greatly depends on the network architecture and training method. In this paper we describe an R implementation of a recurrent neural network trained by the Extended Kalman Filter. For the implementation of the network we used the Matrix package that allows efficient vector-matrix and matrix-matrix operations. We tested the performance of our R implementation comparing it with a pure C++ implementation and we showed that R can achieve about 75% of the C++ programs. Considering the other advantages of R, our results recommend R as a serious alternative to classical programming languages for high performance implementations of neural networks.
Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin
1990-01-01
Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.
PARTICLE SWARM OPTIMIZATION (PSO FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN
Directory of Open Access Journals (Sweden)
Arie Rachmad Syulistyo
2016-02-01
Full Text Available Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO in Convolutional Neural Networks (CNNs, which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN. The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.
Orhan, A Emin; Ma, Wei Ji
2017-07-26
Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task specific operations.
A generalized LSTM-like training algorithm for second-order recurrent neural networks.
Monner, Derek; Reggia, James A
2012-01-01
The long short term memory (LSTM) is a second-order recurrent neural network architecture that excels at storing sequential short-term memories and retrieving them many time-steps later. LSTM's original training algorithm provides the important properties of spatial and temporal locality, which are missing from other training approaches, at the cost of limiting its applicability to a small set of network architectures. Here we introduce the generalized long short-term memory(LSTM-g) training algorithm, which provides LSTM-like locality while being applicable without modification to a much wider range of second-order network architectures. With LSTM-g, all units have an identical set of operating instructions for both activation and learning, subject only to the configuration of their local environment in the network; this is in contrast to the original LSTM training algorithm, where each type of unit has its own activation and training instructions. When applied to LSTM architectures with peephole connections, LSTM-g takes advantage of an additional source of back-propagated error which can enable better performance than the original algorithm. Enabled by the broad architectural applicability of LSTM-g, we demonstrate that training recurrent networks engineered for specific tasks can produce better results than single-layer networks. We conclude that LSTM-g has the potential to both improve the performance and broaden the applicability of spatially and temporally local gradient-based training algorithms for recurrent neural networks. Copyright © 2011 Elsevier Ltd. All rights reserved.
Toward the training of feed-forward neural networks with the D-optimum input sequence.
Witczak, Marcin
2006-03-01
The problem under consideration is to obtain a measurement schedule for training neural networks. This task is perceived as an experimental design in a given design space that is obtained in such a way as to minimize the difference between the neural network and the system being considered. This difference can be expressed in many different ways and one of them, namely, the D-optimality criterion is used in this paper. In particular, the paper presents a unified and comprehensive treatment of this problem by discussing the existing and previously unpublished properties of the optimum experimental design (OED) for neural networks. The consequences of the above properties are discussed as well. A hybrid algorithm that can be used for both the training and data development of neural networks is another important contribution of this paper. A careful analysis of the algorithm is presented and its comprehensive convergence analysis with the help of the Lyapunov method are given. The paper contains a number of numerical examples that justify the application of the OED theory for neural networks. Moreover, an industrial application example is given that deals with the valve actuator.
Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling
Mohamadian, Masoumeh; Afarideh, Hossein; Ghergherehchi, Mitra
2017-01-01
The cyclotron cavity presented in this paper is modeled by a feed-forward neural network trained by the authors’ optimized back-propagation (BP) algorithm. The training samples were obtained from simulation results that are for a number of defined situations and parameters and were achieved parametrically using MWS CST software; furthermore, the conventional BP algorithm with different hidden-neuron numbers, structures, and other optimal parameters such as learning rate that are applied for our purpose was also used here. The present study shows that an optimized FFN can be used to estimate the cyclotron-model parameters with an acceptable error function. A neural network trained by an optimized algorithm therefore shows a proper approximation and an acceptable ability regarding the modeling of the proposed structure. The cyclotron-cavity parameter-modeling results demonstrate that an FNN that is trained by the optimized algorithm could be a suitable method for the estimation of the design parameters in this case.
Reward-based training of recurrent neural networks for cognitive and value-based tasks
Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing
2017-01-01
Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal’s internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task. DOI: http://dx.doi.org/10.7554/eLife.21492.001 PMID:28084991
An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning
Directory of Open Access Journals (Sweden)
Esmond Mok
2013-09-01
Full Text Available Ubiquitous positioning provides continuous positional information in both indoor and outdoor environments for a wide spectrum of location based service (LBS applications. With the rapid development of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals propagated from the Wi-Fi access points (APs namely received signal strength (RSS have been cleverly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is proposed. This algorithm is based on the correlation between the initial parameter setting for neural network training and output of the mean square error to obtain better modeling of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can significantly improve the neural network training surface to achieve the highest possible accuracy of the Wi-Fi fingerprinting positioning method.
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....
Directory of Open Access Journals (Sweden)
H Francis Song
2016-02-01
Full Text Available The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, "trained" networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale's principle, which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural
Andrade, Andre; Costa, Marcelo; Paolucci, Leopoldo; Braga, Antônio; Pires, Flavio; Ugrinowitsch, Herbert; Menzel, Hans-Joachim
2015-01-01
The aim of this study was to present a new training algorithm using artificial neural networks called multi-objective least absolute shrinkage and selection operator (MOBJ-LASSO) applied to the classification of dynamic gait patterns. The movement pattern is identified by 20 characteristics from the three components of the ground reaction force which are used as input information for the neural networks in gender-specific gait classification. The classification performance between MOBJ-LASSO (97.4%) and multi-objective algorithm (MOBJ) (97.1%) is similar, but the MOBJ-LASSO algorithm achieved more improved results than the MOBJ because it is able to eliminate the inputs and automatically select the parameters of the neural network. Thus, it is an effective tool for data mining using neural networks. From 20 inputs used for training, MOBJ-LASSO selected the first and second peaks of the vertical force and the force peak in the antero-posterior direction as the variables that classify the gait patterns of the different genders.
Bernal, Javier; Torres-Jimenez, Jose
2015-01-01
SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller's scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller's algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller's algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller's algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data.
Wang, Xiao-Jing
2016-01-01
The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, “trained” networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale’s principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity
SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
Graff, Philip; Feroz, Farhan; Hobson, Michael P.; Lasenby, Anthony
2014-06-01
We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a `pre-training' method to obtain a set of network parameters that has empirically been shown to be close to a good solution, followed by further optimization using a regularized variant of Newton's method, where the level of regularization is determined and adjusted automatically; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimize using standard backpropagation techniques. SKYNET employs convergence criteria that naturally prevent overfitting, and also includes a fast algorithm for estimating the accuracy of network outputs. The utility and flexibility of SKYNET are demonstrated by application to a number of toy problems, and to astronomical problems focusing on the recovery of structure from blurred and noisy images, the identification of gamma-ray bursters, and the compression and denoising of galaxy images. The SKYNET software, which is implemented in standard ANSI C and fully parallelized using MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.
Effect of training algorithms on neural networks aided pavement ...
African Journals Online (AJOL)
user
pavement modeling results for training the NN aided inverse analysis is .... Also, the Asphalt Institute's Thickness Design Manual MS-1 recommends ERi as ..... http://www.infrastructurereportcard.org/sites/default/files/RC2009_full_report.pdf ...
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.
On the use of harmony search algorithm in the training of wavelet neural networks
Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline
2015-10-01
Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.
Comparative Analysis of Neural Network Training Methods in Real-time Radiotherapy
Directory of Open Access Journals (Sweden)
Nouri S.
2017-03-01
Full Text Available Background: The motions of body and tumor in some regions such as chest during radiotherapy treatments are one of the major concerns protecting normal tissues against high doses. By using real-time radiotherapy technique, it is possible to increase the accuracy of delivered dose to the tumor region by means of tracing markers on the body of patients. Objective: This study evaluates the accuracy of some artificial intelligence methods including neural network and those of combination with genetic algorithm as well as particle swarm optimization (PSO estimating tumor positions in real-time radiotherapy. Method: One hundred recorded signals of three external markers were used as input data. The signals from 3 markers thorough 10 breathing cycles of a patient treated via a cyber-knife for a lung tumor were used as data input. Then, neural network method and its combination with genetic or PSO algorithms were applied determining the tumor locations using MATLAB© software program. Results: The accuracies were obtained 0.8%, 12% and 14% in neural network, genetic and particle swarm optimization algorithms, respectively. Conclusion: The internal target volume (ITV should be determined based on the applied neural network algorithm on training steps.
Comparative Analysis of Neural Network Training Methods in Real-time Radiotherapy.
Nouri, S; Hosseini Pooya, S M; Soltani Nabipour, J
2017-03-01
The motions of body and tumor in some regions such as chest during radiotherapy treatments are one of the major concerns protecting normal tissues against high doses. By using real-time radiotherapy technique, it is possible to increase the accuracy of delivered dose to the tumor region by means of tracing markers on the body of patients. This study evaluates the accuracy of some artificial intelligence methods including neural network and those of combination with genetic algorithm as well as particle swarm optimization (PSO) estimating tumor positions in real-time radiotherapy. One hundred recorded signals of three external markers were used as input data. The signals from 3 markers thorough 10 breathing cycles of a patient treated via a cyber-knife for a lung tumor were used as data input. Then, neural network method and its combination with genetic or PSO algorithms were applied determining the tumor locations using MATLAB© software program. The accuracies were obtained 0.8%, 12% and 14% in neural network, genetic and particle swarm optimization algorithms, respectively. The internal target volume (ITV) should be determined based on the applied neural network algorithm on training steps.
The Evaluation on Data Mining Methods of Horizontal Bar Training Based on BP Neural Network
Directory of Open Access Journals (Sweden)
Zhang Yanhui
2015-01-01
Full Text Available With the rapid development of science and technology, data analysis has become an indispensable part of people’s work and life. Horizontal bar training has multiple categories. It is an emphasis for the re-search of related workers that categories of the training and match should be reduced. The application of data mining methods is discussed based on the problem of reducing categories of horizontal bar training. The BP neural network is applied to the cluster analysis and the principal component analysis, which are used to evaluate horizontal bar training. Two kinds of data mining methods are analyzed from two aspects, namely the operational convenience of data mining and the rationality of results. It turns out that the principal component analysis is more suitable for data processing of horizontal bar training.
A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
Directory of Open Access Journals (Sweden)
Choon Ki Ahn
2010-01-01
Full Text Available A new robust training law, which is called an input/output-to-state stable training law (IOSSTL, is proposed for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.
Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices
Directory of Open Access Journals (Sweden)
Tayfun Gokmen
2017-10-01
Full Text Available In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU devices to convolutional neural networks (CNNs. We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.
Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices
Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried
2017-01-01
In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.
Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.
Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried
2017-01-01
In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.
Training a multilayer neural network for the Euro-dollar (EUR/ USD exchange rate
Directory of Open Access Journals (Sweden)
Jaime Alberto Villamil Torres
2010-04-01
Full Text Available A mathematical tool or model for predicting how an economic variable like the exchange rate (relative price between two currencies will respond is a very important need for investors and policy-makers. Most current techniques are based on statistics, particularly linear time series theory. Artificial neural networks (ANNs are mathematical models which try to emulate biological neural networks’ parallelism and nonlinearity; these models have been successfully applied in Economics and Engineering since the 1980s. ANNs appear to be an alternative for modelling the behaviour of financial variables which resemble (as first approximation a random walk. This paper reports the results of using ANNs for Euro/USD exchange rate trading and the usefulness of the algorithm for chemotaxis leading to training networks thereby maximising an objective function re predicting a trader’s profits. JEL: F310, C450.
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....
High-Dimensional Neural Network Potentials for Organic Reactions and an Improved Training Algorithm.
Gastegger, Michael; Marquetand, Philipp
2015-05-12
Artificial neural networks (NNs) represent a relatively recent approach for the prediction of molecular potential energies, suitable for simulations of large molecules and long time scales. By using NNs to fit electronic structure data, it is possible to obtain empirical potentials of high accuracy combined with the computational efficiency of conventional force fields. However, as opposed to the latter, changing bonding patterns and unusual coordination geometries can be described due to the underlying flexible functional form of the NNs. One of the most promising approaches in this field is the high-dimensional neural network (HDNN) method, which is especially adapted to the prediction of molecular properties. While HDNNs have been mostly used to model solid state systems and surface interactions, we present here the first application of the HDNN approach to an organic reaction, the Claisen rearrangement of allyl vinyl ether to 4-pentenal. To construct the corresponding HDNN potential, a new training algorithm is introduced. This algorithm is termed "element-decoupled" global extended Kalman filter (ED-GEKF) and is based on the decoupled Kalman filter. Using a metadynamics trajectory computed with density functional theory as reference data, we show that the ED-GEKF exhibits superior performance - both in terms of accuracy and training speed - compared to other variants of the Kalman filter hitherto employed in HDNN training. In addition, the effect of including forces during ED-GEKF training on the resulting potentials was studied.
Bennett, C.; Dunne, J. F.; Trimby, S.; Richardson, D.
2017-02-01
A recurrent non-linear autoregressive with exogenous input (NARX) neural network is proposed, and a suitable fully-recurrent training methodology is adapted and tuned, for reconstructing cylinder pressure in multi-cylinder IC engines using measured crank kinematics. This type of indirect sensing is important for cost effective closed-loop combustion control and for On-Board Diagnostics. The challenge addressed is to accurately predict cylinder pressure traces within the cycle under generalisation conditions: i.e. using data not previously seen by the network during training. This involves direct construction and calibration of a suitable inverse crank dynamic model, which owing to singular behaviour at top-dead-centre (TDC), has proved difficult via physical model construction, calibration, and inversion. The NARX architecture is specialised and adapted to cylinder pressure reconstruction, using a fully-recurrent training methodology which is needed because the alternatives are too slow and unreliable for practical network training on production engines. The fully-recurrent Robust Adaptive Gradient Descent (RAGD) algorithm, is tuned initially using synthesised crank kinematics, and then tested on real engine data to assess the reconstruction capability. Real data is obtained from a 1.125 l, 3-cylinder, in-line, direct injection spark ignition (DISI) engine involving synchronised measurements of crank kinematics and cylinder pressure across a range of steady-state speed and load conditions. The paper shows that a RAGD-trained NARX network using both crank velocity and crank acceleration as input information, provides fast and robust training. By using the optimum epoch identified during RAGD training, acceptably accurate cylinder pressures, and especially accurate location-of-peak-pressure, can be reconstructed robustly under generalisation conditions, making it the most practical NARX configuration and recurrent training methodology for use on production engines.
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.
Lu, Thomas; Pham, Timothy; Liao, Jason
2011-01-01
This paper presents the development of a fuzzy logic function trained by an artificial neural network to classify the system noise temperature (SNT) of antennas in the NASA Deep Space Network (DSN). The SNT data were classified into normal, marginal, and abnormal classes. The irregular SNT pattern was further correlated with link margin and weather data. A reasonably good correlation is detected among high SNT, low link margin and the effect of bad weather; however we also saw some unexpected non-correlations which merit further study in the future.
EEG signal classification using PSO trained RBF neural network for epilepsy identification
Directory of Open Access Journals (Sweden)
Sandeep Kumar Satapathy
Full Text Available The electroencephalogram (EEG is a low amplitude signal generated in the brain, as a result of information flow during the communication of several neurons. Hence, careful analysis of these signals could be useful in understanding many human brain disorder diseases. One such disease topic is epileptic seizure identification, which can be identified via a classification process of the EEG signal after preprocessing with the discrete wavelet transform (DWT. To classify the EEG signal, we used a radial basis function neural network (RBFNN. As shown herein, the network can be trained to optimize the mean square error (MSE by using a modified particle swarm optimization (PSO algorithm. The key idea behind the modification of PSO is to introduce a method to overcome the problem of slow searching in and around the global optimum solution. The effectiveness of this procedure was verified by an experimental analysis on a benchmark dataset which is publicly available. The result of our experimental analysis revealed that the improvement in the algorithm is significant with respect to RBF trained by gradient descent and canonical PSO. Here, two classes of EEG signals were considered: the first being an epileptic and the other being non-epileptic. The proposed method produced a maximum accuracy of 99% as compared to the other techniques. Keywords: Electroencephalography, Radial basis function neural network, Particle swarm optimization, Discrete wavelet transform, Machine learning
Song, Qing; Wu, Yilei; Soh, Yeng Chai
2008-11-01
For a recurrent neural network (RNN), its transient response is a critical issue, especially for real-time signal processing applications. The conventional RNN training algorithms, such as backpropagation through time (BPTT) and real-time recurrent learning (RTRL), have not adequately addressed this problem because they suffer from low convergence speed. While increasing the learning rate may help to improve the performance of the RNN, it can result in unstable training in terms of weight divergence. Therefore, an optimal tradeoff between RNN training speed and weight convergence is desired. In this paper, a robust adaptive gradient-descent (RAGD) training algorithm of RNN is developed based on a novel RNN hybrid training concept. It switches the training patterns between standard real-time online backpropagation (BP) and RTRL according to the derived convergence and stability conditions. The weight convergence and L(2)-stability of the algorithm are derived via the conic sector theorem. The optimized adaptive learning maximizes the training speed of the RNN for each weight update without violating the stability and convergence criteria. Computer simulations are carried out to demonstrate the applicability of the theoretical results.
Combined Ozone Retrieval From METOP Sensors Using META-Training Of Deep Neural Networks
Felder, Martin; Sehnke, Frank; Kaifel, Anton
2013-12-01
The newest installment of our well-proven Neural Net- work Ozone Retrieval System (NNORSY) combines the METOP sensors GOME-2 and IASI with cloud information from AVHRR. Through the use of advanced meta- learning techniques like automatic feature selection and automatic architecture search applied to a set of deep neural networks, having at least two or three hidden layers, we have been able to avoid many technical issues normally encountered during the construction of such a joint retrieval system. This has been made possible by harnessing the processing power of modern consumer graphics cards with high performance graphic processors (GPU), which decreases training times by about two orders of magnitude. The system was trained on data from 2009 and 2010, including target ozone profiles from ozone sondes, ACE- FTS and MLS-AURA. To make maximum use of tropospheric information in the spectra, the data were partitioned into several sets of different cloud fraction ranges with the GOME-2 FOV, on which specialized retrieval networks are being trained. For the final ozone retrieval processing the different specialized networks are combined. The resulting retrieval system is very stable and does not show any systematic dependence on solar zenith angle, scan angle or sensor degradation. We present several sensitivity studies with regard to cloud fraction and target sensor type, as well as the performance in several latitude bands and with respect to independent validation stations. A visual cross-comparison against high-resolution ozone profiles from the KNMI EUMETSAT Ozone SAF product has also been performed and shows some distinctive features which we will briefly discuss. Overall, we demonstrate that a complex retrieval system can now be constructed with a minimum of ma- chine learning knowledge, using automated algorithms for many design decisions previously requiring expert knowledge. Provided sufficient training data and computation power of GPUs is available, the
Grinsven, M.J.J.P. van; Ginneken, B. van; Hoyng, C.B.; Theelen, T.; Sanchez, C.I.
2016-01-01
Convolutional neural networks (CNNs) are deep learning network architectures that have pushed forward the state-of-the-art in a range of computer vision applications and are increasingly popular in medical image analysis. However, training of CNNs is time-consuming and challenging. In medical image
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Tajbakhsh, Nima; Shin, Jae Y; Gurudu, Suryakanth R; Hurst, R Todd; Kendall, Christopher B; Gotway, Michael B; Jianming Liang
2016-05-01
Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.
Nigam, Nilay; Bessie Amali, D. Geraldine
2017-11-01
Pollutant Level Predicator is a system which helps in predicting the amount of pollutants in a specific region. The system uses historic data in order to predict the value for the new input. The prediction system uses Artificial Neural Networks (ANN) trained with different optimization algorithms to classify the pollution level into several classes. This research paper assesses and analyses various techniques which can be used to predict the level of pollutant in Delhi. This study uses daily mean air temperature, relative humidity, wind speed and concentration of PM2.5 in Anand Vihar area of Delhi for a period of 2 years (2015 to 2016). Experimental results show that a ANN trained with Galactic swarm optimization algorithm produces a more accurate predication compared to other optimization algorithms.
A pre-trained convolutional neural network based method for thyroid nodule diagnosis.
Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing
2017-01-01
In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.
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...
Evaluation of tactical training in team handball by means of artificial neural networks.
Hassan, Amr; Schrapf, Norbert; Ramadan, Wael; Tilp, Markus
2017-04-01
While tactical performance in competition has been analysed extensively, the assessment of training processes of tactical behaviour has rather been neglected in the literature. Therefore, the purpose of this study is to provide a methodology to assess the acquisition and implementation of offensive tactical behaviour in team handball. The use of game analysis software combined with an artificial neural network (ANN) software enabled identifying tactical target patterns from high level junior players based on their positions during offensive actions. These patterns were then trained by an amateur junior handball team (n = 14, 17 (0.5) years)). Following 6 weeks of tactical training an exhibition game was performed where the players were advised to use the target patterns as often as possible. Subsequently, the position data of the game was analysed with an ANN. The test revealed that 58% of the played patterns could be related to the trained target patterns. The similarity between executed patterns and target patterns was assessed by calculating the mean distance between key positions of the players in the game and the target pattern which was 0.49 (0.20) m. In summary, the presented method appears to be a valid instrument to assess tactical training.
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
simulated process and compared. The closing chapter describes some practical experiments, where the different control concepts and training methods are tested on the same practical process operating in very noisy environments. All tests confirm that neural networks also have the potential to be trained......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...
Pre-trained convolutional neural networks as feature extractors for tuberculosis detection.
Lopes, U K; Valiati, J F
2017-10-01
It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists. Significant research can be found on automating diagnosis by applying computational techniques to medical images, thereby eliminating the need for individual image analysis and greatly diminishing overall costs. In addition, recent improvements on deep learning accomplished excellent results classifying images on diverse domains, but its application for tuberculosis diagnosis remains limited. Thus, the focus of this work is to produce an investigation that will advance the research in the area, presenting three proposals to the application of pre-trained convolutional neural networks as feature extractors to detect the disease. The proposals presented in this work are implemented and compared to the current literature. The obtained results are competitive with published works demonstrating the potential of pre-trained convolutional networks as medical image feature extractors. Copyright © 2017 Elsevier Ltd. All rights reserved.
Manifold absolute pressure estimation using neural network with hybrid training algorithm.
Muslim, Mohd Taufiq; Selamat, Hazlina; Alimin, Ahmad Jais; Haniff, Mohamad Fadzli
2017-01-01
In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.
Manifold absolute pressure estimation using neural network with hybrid training algorithm.
Directory of Open Access Journals (Sweden)
Mohd Taufiq Muslim
Full Text Available In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM algorithm, Bayesian Regularization (BR algorithm and Particle Swarm Optimization (PSO algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS. The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.
Directory of Open Access Journals (Sweden)
S. P. Kundas
2010-01-01
Full Text Available A review of the existing models and methods for forecasting chemical substances' migration in soil is contained in the paper. The paper shows that the most effective decision for solving ecological tasks in this field is an application of artificial neural networks using training «with a tutor» on the basis of an inverse error propagation algorithm. Corresponding structures of neural networks for solution of the given problem have been developed in the paper.A new method for artificial neural network training based on the modification of an inverse error propagation algorithm while using an additional signal is proposed in the paper. The given method allows to achieve 100% convergence in the forecasting problems pertaining to chemical substances' migration in soil.
Directory of Open Access Journals (Sweden)
Tayfun Gokmen
2016-07-01
Full Text Available In recent years, deep neural networks (DNN have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs, however, is universally considered as time consuming and computationally intensive task that demands datacenter-scale computational resources recruited for many days. Here we propose a concept of resistive processing unit (RPU devices that can potentially accelerate DNN training by orders of magnitude while using much less power. The proposed RPU device can store and update the weight values locally thus minimizing data movement during training and allowing to fully exploit the locality and the parallelism of the training algorithm. We evaluate the effect of various RPU device features/non-idealities and system parameters on performance in order to derive the device and system level specifications for implementation of an accelerator chip for DNN training in a realistic CMOS-compatible technology. For large DNNs with about 1 billion weights this massively parallel RPU architecture can achieve acceleration factors of 30,000X compared to state-of-the-art microprocessors while providing power efficiency of 84,000 GigaOps/s/W. Problems that currently require days of training on a datacenter-size cluster with thousands of machines can be addressed within hours on a single RPU accelerator. A system consisting of a cluster of RPU accelerators will be able to tackle Big Data problems with trillions of parameters that is impossible to address today like, for example, natural speech recognition and translation between all world languages, real-time analytics on large streams of business and scientific data, integration and analysis of multimodal sensory data flows from a massive number of IoT (Internet of Things sensors.
Gokmen, Tayfun; Vlasov, Yurii
2016-01-01
In recent years, deep neural networks (DNN) have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs, however, is universally considered as time consuming and computationally intensive task that demands datacenter-scale computational resources recruited for many days. Here we propose a concept of resistive processing unit (RPU) devices that can potentially accelerate DNN training by orders of magnitude while using much less power. The proposed RPU device can store and update the weight values locally thus minimizing data movement during training and allowing to fully exploit the locality and the parallelism of the training algorithm. We evaluate the effect of various RPU device features/non-idealities and system parameters on performance in order to derive the device and system level specifications for implementation of an accelerator chip for DNN training in a realistic CMOS-compatible technology. For large DNNs with about 1 billion weights this massively parallel RPU architecture can achieve acceleration factors of 30, 000 × compared to state-of-the-art microprocessors while providing power efficiency of 84, 000 GigaOps∕s∕W. Problems that currently require days of training on a datacenter-size cluster with thousands of machines can be addressed within hours on a single RPU accelerator. A system consisting of a cluster of RPU accelerators will be able to tackle Big Data problems with trillions of parameters that is impossible to address today like, for example, natural speech recognition and translation between all world languages, real-time analytics on large streams of business and scientific data, integration, and analysis of multimodal sensory data flows from a massive number of IoT (Internet of Things) sensors.
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...
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.
Villarreal, James A.
1991-01-01
A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.
Kalderstam, Jonas; Edén, Patrik; Bendahl, Pär-Ola; Strand, Carina; Fernö, Mårten; Ohlsson, Mattias
2013-06-01
The concordance index (c-index) is the standard way of evaluating the performance of prognostic models in the presence of censored data. Constructing prognostic models using artificial neural networks (ANNs) is commonly done by training on error functions which are modified versions of the c-index. Our objective was to demonstrate the capability of training directly on the c-index and to evaluate our approach compared to the Cox proportional hazards model. We constructed a prognostic model using an ensemble of ANNs which were trained using a genetic algorithm. The individual networks were trained on a non-linear artificial data set divided into a training and test set both of size 2000, where 50% of the data was censored. The ANNs were also trained on a data set consisting of 4042 patients treated for breast cancer spread over five different medical studies, 2/3 used for training and 1/3 used as a test set. A Cox model was also constructed on the same data in both cases. The two models' c-indices on the test sets were then compared. The ranking performance of the models is additionally presented visually using modified scatter plots. Cross validation on the cancer training set did not indicate any non-linear effects between the covariates. An ensemble of 30 ANNs with one hidden neuron was therefore used. The ANN model had almost the same c-index score as the Cox model (c-index=0.70 and 0.71, respectively) on the cancer test set. Both models identified similarly sized low risk groups with at most 10% false positives, 49 for the ANN model and 60 for the Cox model, but repeated bootstrap runs indicate that the difference was not significant. A significant difference could however be seen when applied on the non-linear synthetic data set. In that case the ANN ensemble managed to achieve a c-index score of 0.90 whereas the Cox model failed to distinguish itself from the random case (c-index=0.49). We have found empirical evidence that ensembles of ANN models can be
Vyas, Bhargav Y; Das, Biswarup; Maheshwari, Rudra Prakash
2016-08-01
This paper presents the Chebyshev neural network (ChNN) as an improved artificial intelligence technique for power system protection studies and examines the performances of two ChNN learning algorithms for fault classification of series compensated transmission line. The training algorithms are least-square Levenberg-Marquardt (LSLM) and recursive least-square algorithm with forgetting factor (RLSFF). The performances of these algorithms are assessed based on their generalization capability in relating the fault current parameters with an event of fault in the transmission line. The proposed algorithm is fast in response as it utilizes postfault samples of three phase currents measured at the relaying end corresponding to half-cycle duration only. After being trained with only a small part of the generated fault data, the algorithms have been tested over a large number of fault cases with wide variation of system and fault parameters. Based on the studies carried out in this paper, it has been found that although the RLSFF algorithm is faster for training the ChNN in the fault classification application for series compensated transmission lines, the LSLM algorithm has the best accuracy in testing. The results prove that the proposed ChNN-based method is accurate, fast, easy to design, and immune to the level of compensations. Thus, it is suitable for digital relaying applications.
Training Knowledge Bots for Physics-Based Simulations Using Artificial Neural Networks
Samareh, Jamshid A.; Wong, Jay Ming
2014-01-01
Millions of complex physics-based simulations are required for design of an aerospace vehicle. These simulations are usually performed by highly trained and skilled analysts, who execute, monitor, and steer each simulation. Analysts rely heavily on their broad experience that may have taken 20-30 years to accumulate. In addition, the simulation software is complex in nature, requiring significant computational resources. Simulations of system of systems become even more complex and are beyond human capacity to effectively learn their behavior. IBM has developed machines that can learn and compete successfully with a chess grandmaster and most successful jeopardy contestants. These machines are capable of learning some complex problems much faster than humans can learn. In this paper, we propose using artificial neural network to train knowledge bots to identify the idiosyncrasies of simulation software and recognize patterns that can lead to successful simulations. We examine the use of knowledge bots for applications of computational fluid dynamics (CFD), trajectory analysis, commercial finite-element analysis software, and slosh propellant dynamics. We will show that machine learning algorithms can be used to learn the idiosyncrasies of computational simulations and identify regions of instability without including any additional information about their mathematical form or applied discretization approaches.
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
Directory of Open Access Journals (Sweden)
Mark D McDonnell
Full Text Available Recent advances in training deep (multi-layer architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM approach, which also enables a very rapid training time (∼ 10 minutes. Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random 'receptive field' sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.
McDonnell, Mark D; Tissera, Migel D; Vladusich, Tony; van Schaik, André; Tapson, Jonathan
2015-01-01
Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random 'receptive field' sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.
Satellite image analysis using neural networks
Sheldon, Roger A.
1990-01-01
The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.
Demonstration of Self-Training Autonomous Neural Networks in Space Vehicle Docking Simulations
Patrick, M. Clinton; Thaler, Stephen L.; Stevenson-Chavis, Katherine
2006-01-01
Neural Networks have been under examination for decades in many areas of research, with varying degrees of success and acceptance. Key goals of computer learning, rapid problem solution, and automatic adaptation have been elusive at best. This paper summarizes efforts at NASA's Marshall Space Flight Center harnessing such technology to autonomous space vehicle docking for the purpose of evaluating applicability to future missions.
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
van Grinsven, Mark J J P; van Ginneken, Bram; Hoyng, Carel B; Theelen, Thomas; Sanchez, Clara I
2016-05-01
Convolutional neural networks (CNNs) are deep learning network architectures that have pushed forward the state-of-the-art in a range of computer vision applications and are increasingly popular in medical image analysis. However, training of CNNs is time-consuming and challenging. In medical image analysis tasks, the majority of training examples are easy to classify and therefore contribute little to the CNN learning process. In this paper, we propose a method to improve and speed-up the CNN training for medical image analysis tasks by dynamically selecting misclassified negative samples during training. Training samples are heuristically sampled based on classification by the current status of the CNN. Weights are assigned to the training samples and informative samples are more likely to be included in the next CNN training iteration. We evaluated and compared our proposed method by training a CNN with (SeS) and without (NSeS) the selective sampling method. We focus on the detection of hemorrhages in color fundus images. A decreased training time from 170 epochs to 60 epochs with an increased performance-on par with two human experts-was achieved with areas under the receiver operating characteristics curve of 0.894 and 0.972 on two data sets. The SeS CNN statistically outperformed the NSeS CNN on an independent test set.
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....
Directory of Open Access Journals (Sweden)
Jeng-Fung Chen
2014-10-01
Full Text Available Predicting student academic performance with a high accuracy facilitates admission decisions and enhances educational services at educational institutions. This raises the need to propose a model that predicts student performance, based on the results of standardized exams, including university entrance exams, high school graduation exams, and other influential factors. In this study, an approach to the problem based on the artificial neural network (ANN with the two meta-heuristic algorithms inspired by cuckoo birds and their lifestyle, namely, Cuckoo Search (CS and Cuckoo Optimization Algorithm (COA is proposed. In particular, we used previous exam results and other factors, such as the location of the student’s high school and the student’s gender as input variables, and predicted the student academic performance. The standard CS and standard COA were separately utilized to train the feed-forward network for prediction. The algorithms optimized the weights between layers and biases of the neuron network. The simulation results were then discussed and analyzed to investigate the prediction ability of the neural network trained by these two algorithms. The findings demonstrated that both CS and COA have potential in training ANN and ANN-COA obtained slightly better results for predicting student academic performance in this case. It is expected that this work may be used to support student admission procedures and strengthen the service system in educational institutions.
Directory of Open Access Journals (Sweden)
Georgios Papantonopoulos
Full Text Available There is neither a single clinical, microbiological, histopathological or genetic test, nor combinations of them, to discriminate aggressive periodontitis (AgP from chronic periodontitis (CP patients. We aimed to estimate probability density functions of clinical and immunologic datasets derived from periodontitis patients and construct artificial neural networks (ANNs to correctly classify patients into AgP or CP class. The fit of probability distributions on the datasets was tested by the Akaike information criterion (AIC. ANNs were trained by cross entropy (CE values estimated between probabilities of showing certain levels of immunologic parameters and a reference mode probability proposed by kernel density estimation (KDE. The weight decay regularization parameter of the ANNs was determined by 10-fold cross-validation. Possible evidence for 2 clusters of patients on cross-sectional and longitudinal bone loss measurements were revealed by KDE. Two to 7 clusters were shown on datasets of CD4/CD8 ratio, CD3, monocyte, eosinophil, neutrophil and lymphocyte counts, IL-1, IL-2, IL-4, INF-γ and TNF-α level from monocytes, antibody levels against A. actinomycetemcomitans (A.a. and P.gingivalis (P.g.. ANNs gave 90%-98% accuracy in classifying patients into either AgP or CP. The best overall prediction was given by an ANN with CE of monocyte, eosinophil, neutrophil counts and CD4/CD8 ratio as inputs. ANNs can be powerful in classifying periodontitis patients into AgP or CP, when fed by CE values based on KDE. Therefore ANNs can be employed for accurate diagnosis of AgP or CP by using relatively simple and conveniently obtained parameters, like leukocyte counts in peripheral blood. This will allow clinicians to better adapt specific treatment protocols for their AgP and CP patients.
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
Directory of Open Access Journals (Sweden)
Gotzon Toral Madariaga
2013-02-01
Full Text Available 0 0 1 121 669 USAL 5 1 789 14.0 Normal 0 21 false false false ES JA X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Tabla normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:Calibri; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-ansi-language:ES; mso-fareast-language:EN-US;} Media control is no longer exclusively in the hands of professional broadcasters. New educational projects must empower users so that they can exercise their digital citizenship. As well as acquiring essential technical skills to move in an interconnected world, emotional literacy is also indispensable for people to desire to take part effectively in this augmented community. So, besides teaching audiovisual technology, this project seeks to re-program the relationship that students develop with a situation that is typically stressful. We propose an expanded practice that enables students to recognize and voluntarily activate their communication biology. This way, users can become actors in new communication networks, and global communication flow will be more plural and richer.
Meza-Kubo, Victoria; Morán, Alberto L; Carrillo, Ivan; Galindo, Gilberto; García-Canseco, Eloisa
2016-08-01
The use of Ambient Assisted Living (AAL) technologies as a means to cope with problems that arise due to an increasing and aging population is becoming usual. AAL technologies are used to prevent, cure and improve the wellness and health conditions of the elderly. However, their adoption and use by older adults is still a major challenge. User Experience (UX) evaluations aim at aiding on this task, by identifying the experience that a user has while interacting with an AAL technology under particular conditions. This may help designing better products and improve user engagement and adoption of AAL solutions. However, evaluating the UX of AAL technologies is a difficult task, due to the inherent limitations of their subjects and of the evaluation methods. In this study, we validated the feasibility of assessing the UX of older adults while they use a cognitive stimulation application using a neural network trained to recognize pleasant and unpleasant emotions from electroencephalography (EEG) signals by contrasting our results with those of additional self-report and qualitative analysis UX evaluations. Our study results provide evidence about the feasibility of assessing the UX of older adults using a neural network that take as input the EEG signals; the classification accuracy of our neural network ranges from 60.87% to 82.61%. As future work we will conduct additional UX evaluation studies using the three different methods, in order to appropriately validate these results. Copyright © 2016 Elsevier Inc. All rights reserved.
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...
Subramaniam, Karuna; Luks, Tracy L; Fisher, Melissa; Simpson, Gregory V; Nagarajan, Srikantan; Vinogradov, Sophia
2012-02-23
Schizophrenia patients suffer from severe cognitive deficits, such as impaired reality monitoring. Reality monitoring is the ability to distinguish the source of internal experiences from outside reality. During reality monitoring tasks, schizophrenia patients make errors identifying "I made it up" items, and even during accurate performance, they show abnormally low activation of the medial prefrontal cortex (mPFC), a region that supports self-referential cognition. We administered 80 hr of computerized training of cognitive processes to schizophrenia patients and found improvement in reality monitoring that correlated with increased mPFC activity. In contrast, patients in a computer games control condition did not show any behavioral or neural improvements. Notably, recovery in mPFC activity after training was associated with improved social functioning 6 months later. These findings demonstrate that a serious behavioral deficit in schizophrenia, and its underlying neural dysfunction, can be improved by well-designed computerized cognitive training, resulting in better quality of life. Copyright © 2012 Elsevier Inc. All rights reserved.
Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate
National Research Council Canada - National Science Library
Jaime Alberto Villamil Torres; Jesús Alberto Delgado Rivera
2010-01-01
... (as first approximation) a random walk. This paper reports the results of using ANNs for Euro/USD exchange rate trading and the usefulness of the algorithm for chemotaxis leading to training networks thereby maximising an objective function re predicting a trader’s profits. JEL: F310, C450.
Pediatric Nutritional Requirements Determination with Neural Networks
Karlık, Bekir; Ece, Aydın
1998-01-01
To calculate daily nutritional requirements of children, a computer program has been developed based upon neural network. Three parameters, daily protein, energy and water requirements, were calculated through trained artificial neural networks using a database of 312 children The results were compared with those of calculated from dietary requirements tables of World Health Organisation. No significant difference was found between two calculations. In conclusion, a simple neural network may ...
Nonlinear System Identification Using Neural Networks Trained with Natural Gradient Descent
Directory of Open Access Journals (Sweden)
Ibnkahla Mohamed
2003-01-01
Full Text Available We use natural gradient (NG learning neural networks (NNs for modeling and identifying nonlinear systems with memory. The nonlinear system is comprised of a discrete-time linear filter followed by a zero-memory nonlinearity . The NN model is composed of a linear adaptive filter followed by a two-layer memoryless nonlinear NN. A Kalman filter-based technique and a search-and-converge method have been employed for the NG algorithm. It is shown that the NG descent learning significantly outperforms the ordinary gradient descent and the Levenberg-Marquardt (LM procedure in terms of convergence speed and mean squared error (MSE performance.
Fin-and-tube condenser performance evaluation using neural networks
Energy Technology Data Exchange (ETDEWEB)
Zhao, Ling-Xiao [Institute of Refrigeration and Cryogenics, Shanghai Jiaotong University, Shanghai 200240 (China); Zhang, Chun-Lu [China R and D Center, Carrier Corporation, No. 3239 Shen Jiang Road, Shanghai 201206 (China)
2010-05-15
The paper presents neural network approach to performance evaluation of the fin-and-tube air-cooled condensers which are widely used in air-conditioning and refrigeration systems. Inputs of the neural network include refrigerant and air-flow rates, refrigerant inlet temperature and saturated temperature, and entering air dry-bulb temperature. Outputs of the neural network consist of the heating capacity and the pressure drops on both refrigerant and air sides. The multi-input multi-output (MIMO) neural network is separated into multi-input single-output (MISO) neural networks for training. Afterwards, the trained MISO neural networks are combined into a MIMO neural network, which indicates that the number of training data sets is determined by the biggest MISO neural network not the whole MIMO network. Compared with a validated first-principle model, the standard deviations of neural network models are less than 1.9%, and all errors fall into {+-}5%. (author)
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…
Padgett, Mary L.; Desai, Utpal; Roppel, T.A.; White, Charles R.
1993-01-01
A design procedure is suggested for neural networks which accommodates the inclusion of such knowledge-based systems techniques as fuzzy logic and pairwise comparisons. The use of these procedures in the design of applications combines qualitative and quantitative factors with empirical data to yield a model with justifiable design and parameter selection procedures. The procedure is especially relevant to areas of back-propagation neural network design which are highly responsive to the use of precisely recorded expert knowledge.
Piotrowski, Adam P.; Osuch, Marzena; Napiorkowski, Maciej J.; Rowinski, Pawel M.; Napiorkowski, Jaroslaw J.
2014-03-01
Nature-inspired metaheuristics found various applications in different fields of science, including the problem of artificial neural networks (ANN) training. However, very versatile opinions regarding the performance of metaheuristics applied to ANN training may be found in the literature. Both nature-inspired metaheuristics and ANNs are widely applied to various geophysical and environmental problems. Among them the water temperature forecasting in a natural river, especially in colder climate zones where the seasonality plays important role, is of great importance, as water temperature has strong impact on aquatic life and chemistry. As the impact of possible future climate change on water temperature is not trivial, models are needed to allow projection of streamwater temperature based on simple hydro-meteorological variables. In this paper the detailed comparison of the performance of nature-inspired optimization methods and Levenberg-Marquardt (LM) algorithm in ANNs training is performed, based on the case study of water temperature forecasting in a natural stream, namely Biala Tarnowska river in southern Poland. Over 50 variants of 22 various metaheuristics, including a large number of Differential Evolution, as well as some Particle Swarm Optimization, Evolution Strategies, multialgorithms and Direct Search methods are compared with LM algorithm on ANN training for the described case study. The impact of population size and some control parameters of particular metaheuristics on the ANN training performance are verified. It is found that despite widely claimed large improvement in nature-inspired methods during last years, the vast majority of them are still outperformed by LM algorithm on the selected problem. The only methods that, based on this case study, seem competitive to LM algorithm in terms of the final performance (but not speed) are Differential Evolution algorithms that benefit from the concept of Global and Local neighborhood-based mutation
Neural network approach to parton distributions fitting
Piccione, Andrea; Forte, Stefano; Latorre, Jose I.; Rojo, Joan; Piccione, Andrea; Rojo, Joan
2006-01-01
We will show an application of neural networks to extract information on the structure of hadrons. A Monte Carlo over experimental data is performed to correctly reproduce data errors and correlations. A neural network is then trained on each Monte Carlo replica via a genetic algorithm. Results on the proton and deuteron structure functions, and on the nonsinglet parton distribution will be shown.
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.
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...
Neural network based system for equipment surveillance
Vilim, R.B.; Gross, K.C.; Wegerich, S.W.
1998-04-28
A method and system are disclosed for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process. 33 figs.
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.
Energy Technology Data Exchange (ETDEWEB)
Sun, W; Jiang, M; Yin, F [Duke University Medical Center, Durham, NC (United States)
2016-06-15
Purpose: Dynamic tracking of moving organs, such as lung and liver tumors, under radiation therapy requires prediction of organ motions prior to delivery. The shift of moving organ may change a lot due to huge transform of respiration at different periods. This study aims to reduce the influence of that changes using adjustable training signals and multi-layer perceptron neural network (ASMLP). Methods: Respiratory signals obtained using a Real-time Position Management(RPM) device were used for this study. The ASMLP uses two multi-layer perceptron neural networks(MLPs) to infer respiration position alternately and the training sample will be updated with time. Firstly, a Savitzky-Golay finite impulse response smoothing filter was established to smooth the respiratory signal. Secondly, two same MLPs were developed to estimate respiratory position from its previous positions separately. Weights and thresholds were updated to minimize network errors according to Leverberg-Marquart optimization algorithm through backward propagation method. Finally, MLP 1 was used to predict 120∼150s respiration position using 0∼120s training signals. At the same time, MLP 2 was trained using 30∼150s training signals. Then MLP is used to predict 150∼180s training signals according to 30∼150s training signals. The respiration position is predicted as this way until it was finished. Results: In this experiment, the two methods were used to predict 2.5 minute respiratory signals. For predicting 1s ahead of response time, correlation coefficient was improved from 0.8250(MLP method) to 0.8856(ASMLP method). Besides, a 30% improvement of mean absolute error between MLP(0.1798 on average) and ASMLP(0.1267 on average) was achieved. For predicting 2s ahead of response time, correlation coefficient was improved from 0.61415 to 0.7098.Mean absolute error of MLP method(0.3111 on average) was reduced by 35% using ASMLP method(0.2020 on average). Conclusion: The preliminary results
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.
Mani-Varnosfaderani, Ahmad; Kanginejad, Atefeh; Gilany, Kambiz; Valadkhani, Abolfazl
2016-10-12
The present work deals with the development of a new baseline correction method based on the comparative learning capabilities of artificial neural networks. The developed method uses the Bayes probability theorem for prevention of the occurrence of the over-fitting and finding a generalized baseline. The developed method has been applied on simulated and real metabolomic gas-chromatography (GC) and Raman data sets. The results revealed that the proposed method can be used to handle different types of baselines with cave, convex, curvelinear, triangular and sinusoidal patterns. For further evaluation of the performances of this method, it has been compared with benchmarking baseline correction methods such as corner-cutting (CC), morphological weighted penalized least squares (MPLS), adaptive iteratively-reweighted penalized least squares (airPLS) and iterative polynomial fitting (iPF). In order to compare the methods, the projected difference resolution (PDR) criterion has been calculated for the data before and after the baseline correction procedure. The calculated values of PDR after the baseline correction using iBRANN, airPLS, MPLS, iPF and CC algorithms for the GC metabolomic data were 4.18, 3.64, 3.88, 1.88 and 3.08, respectively. The obtained results in this work demonstrated that the developed iterative Bayesian regularized neural network (iBRANN) method in this work thoroughly detects the baselines and is superior over the CC, MPLS, airPLS and iPF techniques. A graphical user interface has been developed for the suggested algorithm and can be used for easy implementation of the iBRANN algorithm for the correction of different chromatography, NMR and Raman data sets. Copyright © 2016 Elsevier B.V. All rights reserved.
Using Neural Networks in Diagnosing Breast Cancer
National Research Council Canada - National Science Library
Fogel, David
1997-01-01
.... In the current study, evolutionary programming is used to train neural networks and linear discriminant models to detect breast cancer in suspicious and microcalcifications using radiographic features and patient age...
Isolated Speech Recognition Using Artificial Neural Networks
National Research Council Canada - National Science Library
Polur, Prasad
2001-01-01
.... A small size vocabulary containing the words YES and NO is chosen. Spectral features using cepstral analysis are extracted per frame and imported to a feedforward neural network which uses a backpropagation with momentum training algorithm...
Modular representation of layered neural networks.
Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio
2018-01-01
Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.
Hyperbolic Hopfield neural networks.
Kobayashi, M
2013-02-01
In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states.
Neural network optimization, components, and design selection
Weller, Scott W.
1991-01-01
Neural Networks are part of a revived technology which has received a lot of hype in recent years. As is apt to happen in any hyped technology, jargon and predictions make its assimilation and application difficult. Nevertheless, Neural Networks have found use in a number of areas, working on non-trivial and non-contrived problems. For example, one net has been trained to "read", translating English text into phoneme sequences. Other applications of Neural Networks include data base manipulation and the solving of routing and classification types of optimization problems. It was their use in optimization that got me involved with Neural Networks. As it turned out, "optimization" used in this context was somewhat misleading, because while some network configurations could indeed solve certain kinds of optimization problems, the configuring or "training" of a Neural Network itself is an optimization problem, and most of the literature which talked about Neural Nets and optimization in the same breath did not speak to my goal of using Neural Nets to help solve lens optimization problems. I did eventually apply Neural Network to lens optimization, and I will touch on those results. The application of Neural Nets to the problem of lens selection was much more successful, and those results will dominate this paper.
Energy Technology Data Exchange (ETDEWEB)
Parker, E.P.; Rosenthal, S.E.; Trahan, M.W.; Wagner, J.S.
1999-01-22
We are developing a method for analysis of airborne microparticles based on laser ablation of individual molecules in an ion trap mass spectrometer. Airborne particles enter the spectrometer through a differentially-pumped inlet, are detected by light scattered from two CW laser beams, and sampled by a pulsed excimer laser as they pass through the center of the ion trap electrodes. After the laser pulse, the stored ions are separated by conventional ion trap methods. The mass spectra are then analyzed using genetically-trained neural networks (NNs). A number of mass spectra are averaged to obtain training cases which contain a recognizable spectral signature. Averaged spectra for a bacteria and a non-bacteria are shown to the NNs, the response evaluated, and the weights of the connections between neurodes adjusted by a Genetic Algorithm (GA) such that the output from the NN ranges from 0 for non-bacteria to 1 for bacteria. This process is iterated until the population of the GA converges or satisfies predetermined stopping criteria. Using this type of bipolar training we have obtained generalizing NNs able to distinguish five new bacteria from five new non-bacteria, none of which were used in training the NN.
Fu, Xingang; Li, Shuhui; Fairbank, Michael; Wunsch, Donald C; Alonso, Eduardo
2015-09-01
This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC) using an RNN. To successfully and efficiently train an RNN using the LM algorithm, a new forward accumulation through time (FATT) algorithm is proposed to calculate the Jacobian matrix required by the LM algorithm. This paper explores how to incorporate FATT into the LM algorithm. The results show that the combination of the LM and FATT algorithms trains RNNs better than the conventional backpropagation through time algorithm. This paper presents an analytical study on the optimal control of GCCs, including theoretically ideal optimal and suboptimal controllers. To overcome the inapplicability of the optimal GCC controller under practical conditions, a new RNN controller with an improved input structure is proposed to approximate the ideal optimal controller. The performance of an ideal optimal controller and a well-trained RNN controller was compared in close to real-life power converter switching environments, demonstrating that the proposed RNN controller can achieve close to ideal optimal control performance even under low sampling rate conditions. The excellent performance of the proposed RNN controller under challenging and distorted system conditions further indicates the feasibility of using an RNN to approximate optimal control in practical applications.
Memristor-based multilayer neural networks with online gradient descent training.
Soudry, Daniel; Di Castro, Dotan; Gal, Asaf; Kolodny, Avinoam; Kvatinsky, Shahar
2015-10-01
Learning in multilayer neural networks (MNNs) relies on continuous updating of large matrices of synaptic weights by local rules. Such locality can be exploited for massive parallelism when implementing MNNs in hardware. However, these update rules require a multiply and accumulate operation for each synaptic weight, which is challenging to implement compactly using CMOS. In this paper, a method for performing these update operations simultaneously (incremental outer products) using memristor-based arrays is proposed. The method is based on the fact that, approximately, given a voltage pulse, the conductivity of a memristor will increment proportionally to the pulse duration multiplied by the pulse magnitude if the increment is sufficiently small. The proposed method uses a synaptic circuit composed of a small number of components per synapse: one memristor and two CMOS transistors. This circuit is expected to consume between 2% and 8% of the area and static power of previous CMOS-only hardware alternatives. Such a circuit can compactly implement hardware MNNs trainable by scalable algorithms based on online gradient descent (e.g., backpropagation). The utility and robustness of the proposed memristor-based circuit are demonstrated on standard supervised learning tasks.
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....
Deconvolution using a neural network
Energy Technology Data Exchange (ETDEWEB)
Lehman, S.K.
1990-11-15
Viewing one dimensional deconvolution as a matrix inversion problem, we compare a neural network backpropagation matrix inverse with LMS, and pseudo-inverse. This is a largely an exercise in understanding how our neural network code works. 1 ref.
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. .
Quang Truong, Dinh; Ahn, Kyoung Kwan
2014-07-01
An ion polymer metal composite (IPMC) is an electroactive polymer that bends in response to a small applied electric field as a result of mobility of cations in the polymer network and vice versa. This paper presents an innovative and accurate nonlinear black-box model (NBBM) for estimating the bending behavior of IPMC actuators. The model is constructed via a general multilayer perceptron neural network (GMLPNN) integrated with a smart learning mechanism (SLM) that is based on an extended Kalman filter with self-decoupling ability (SDEKF). Here the GMLPNN is built with an ability to autoadjust its structure based on its characteristic vector. Furthermore, by using the SLM based on the SDEKF, the GMLPNN parameters are optimized with small computational effort, and the modeling accuracy is improved. An apparatus employing an IPMC actuator is first set up to investigate the IPMC characteristics and to generate the data for training and validating the model. The advanced NBBM model for the IPMC system is then created with the proper inputs to estimate IPMC tip displacement. Next, the model is optimized using the SLM mechanism with the training data. Finally, the optimized NBBM model is verified with the validating data. A comparison between this model and the previously developed model is also carried out to prove the effectiveness of the proposed modeling technique.
Program Aids Simulation Of Neural Networks
Baffes, Paul T.
1990-01-01
Computer program NETS - Tool for Development and Evaluation of Neural Networks - provides simulation of neural-network algorithms plus software environment for development of such algorithms. Enables user to customize patterns of connections between layers of network, and provides features for saving weight values of network, providing for more precise control over learning process. Consists of translating problem into format using input/output pairs, designing network configuration for problem, and finally training network with input/output pairs until acceptable error reached. Written in C.
Lin, Wei-Qi; Jiang, Jian-Hui; Zhou, Yan-Ping; Wu, Hai-Long; Shen, Guo-Li; Yu, Ru-Qin
2007-01-30
Multilayer feedforward neural networks (MLFNNs) are important modeling techniques widely used in QSAR studies for their ability to represent nonlinear relationships between descriptors and activity. However, the problems of overfitting and premature convergence to local optima still pose great challenges in the practice of MLFNNs. To circumvent these problems, a support vector machine (SVM) based training algorithm for MLFNNs has been developed with the incorporation of particle swarm optimization (PSO). The introduction of the SVM based training mechanism imparts the developed algorithm with inherent capacity for combating the overfitting problem. Moreover, with the implementation of PSO for searching the optimal network weights, the SVM based learning algorithm shows relatively high efficiency in converging to the optima. The proposed algorithm has been evaluated using the Hansch data set. Application to QSAR studies of the activity of COX-2 inhibitors is also demonstrated. The results reveal that this technique provides superior performance to backpropagation (BP) and PSO training neural networks.
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...
National Research Council Canada - National Science Library
J. Jakubski; St. M. Dobosz; K. Major-Gabryś
2013-01-01
.... This paper presents the next part of the study on usefulness of artificial neural networks to support rebonding of green moulding sand, using chosen properties of moulding sands, which can be determined fast...
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
Analysis of neural networks in terms of domain functions
van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, Lambert
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
Extracting knowledge from supervised neural networks in image processing
van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, Lambert; Jain, R.; Abraham, A.; Faucher, C.; van der Zwaag, B.J.
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
Artificial Neural Network Modeling of an Inverse Fluidized Bed ...
African Journals Online (AJOL)
The application of neural networks to model a laboratory scale inverse fluidized bed reactor has been studied. A Radial Basis Function neural network has been successfully employed for the modeling of the inverse fluidized bed reactor. In the proposed model, the trained neural network represents the kinetics of biological ...
The Artifical Neural Network as means for modeling Nonlinear Systems
Drábek Oldøich; Taufer Ivan
1998-01-01
The paper deals with nonlinear system identification based on neural network. The topic of this publication is simulation of training and testing a neural network. A contribution is assigned to technologists which are good at the clasical identification problems but their knowledges about identification based on neural network are only on the stage of theoretical bases.
The Artifical Neural Network as means for modeling Nonlinear Systems
Directory of Open Access Journals (Sweden)
Drábek Oldøich
1998-12-01
Full Text Available The paper deals with nonlinear system identification based on neural network. The topic of this publication is simulation of training and testing a neural network. A contribution is assigned to technologists which are good at the clasical identification problems but their knowledges about identification based on neural network are only on the stage of theoretical bases.
Person Movement Prediction Using Neural Networks
Vintan, Lucian; Gellert, Arpad; Petzold, Jan; Ungerer, Theo
2006-01-01
Ubiquitous systems use context information to adapt appliance behavior to human needs. Even more convenience is reached if the appliance foresees the user's desires and acts proactively. This paper proposes neural prediction techniques to anticipate a person's next movement. We focus on neural predictors (multi-layer perceptron with back-propagation learning) with and without pre-training. The optimal configuration of the neural network is determined by evaluating movement sequences of real p...
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.
Directory of Open Access Journals (Sweden)
Nasir eAhmad
2016-03-01
Full Text Available Attempting to explain the perceptual qualities of pitch has proven to be, and remains, a difficult problem. The wide range of sounds which illicit pitch and a lack of agreement across neurophysiological studies on how pitch is encoded by the brain have made this attempt more difficult. In describing the potential neural mechanisms by which pitch may be processed, a number of neural networks have been proposed and implemented. However, no unsupervised neural networks with biologically accurate cochlear inputs have yet been demonstrated. This paper proposes a simplified system in which pitch representing neurons are easily produced under a highly biological setting. Purely unsupervised regimes of neural network learning are implemented and these prove to be sufficient in identifying the pitch of sounds with a variety of spectral profiles, including missing fundamental sounds.
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...
Woodward, Richard B; Spanias, John A; Hargrove, Levi J
2016-08-01
Powered lower limb prostheses have the ability to provide greater mobility for amputee patients. Such prostheses often have pre-programmed modes which can allow activities such as climbing stairs and descending ramps, something which many amputees struggle with when using non-powered limbs. Previous literature has shown how pattern classification can allow seamless transitions between modes with a high accuracy and without any user interaction. Although accurate, training and testing each subject with their own dependent data is time consuming. By using subject independent datasets, whereby a unique subject is tested against a pooled dataset of other subjects, we believe subject training time can be reduced while still achieving an accurate classification. We present here an intent recognition system using an artificial neural network (ANN) with a scaled conjugate gradient learning algorithm to classify gait intention with user-dependent and independent datasets for six unilateral lower limb amputees. We compare these results against a linear discriminant analysis (LDA) classifier. The ANN was found to have significantly lower classification error (P<;0.05) than LDA with all user-dependent step-types, as well as transitional steps for user-independent datasets. Both types of classifiers are capable of making fast decisions; 1.29 and 2.83 ms for the LDA and ANN respectively. These results suggest that ANNs can provide suitable and accurate offline classification in prosthesis gait prediction.
Su, Feng; Yuan, Peijiang; Wang, Yangzhen; Zhang, Chen
2016-10-01
Artificial neural networks (ANNs) are powerful computational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance (FT), an important property of ANNs, ensures their reliability when significant portions of a network are lost. In this paper, a fault/noise injection-based (FIB) genetic algorithm (GA) is proposed to construct fault-tolerant ANNs. The FT performance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algorithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR (XOR) problem and the overlapping classification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.
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.
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)
Neutron spectrometry using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Vega-Carrillo, Hector Rene [Unidad Academica de Estudios Nucleares, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]|[Unidad Academica de Ing. Electrica, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]|[Unidad Academica de Matematicas, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]. E-mail: fermineutron@yahoo.com; Martin Hernandez-Davila, Victor [Unidad Academica de Estudios Nucleares, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]|[Unidad Academica de Ing. Electrica, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico); Manzanares-Acuna, Eduardo [Unidad Academica de Estudios Nucleares, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico); Mercado Sanchez, Gema A. [Unidad Academica de Matematicas, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico); Pilar Iniguez de la Torre, Maria [Depto. Fisica Teorica, Molecular y Nuclear, Universidad de Valladolid, Valladolid (Spain); Barquero, Raquel [Hospital Universitario Rio Hortega, Valladolid (Spain); Palacios, Francisco; Mendez Villafane, Roberto [Depto. Fisica Teorica, Molecular y Nuclear, Universidad de Valladolid, Valladolid (Spain)]|[Universidad Europea Miguel de Cervantes, C. Padre Julio Chevalier No. 2, 47012 Valladolid (Spain); Arteaga Arteaga, Tarcicio [Unidad Academica de Estudios Nucleares, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]|[Envases de Zacatecas, SA de CV, Parque Industrial de Calera de Victor Rosales, Zac. (Mexico); Manuel Ortiz Rodriguez, Jose [Unidad Academica de Estudios Nucleares, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)]|[Unidad Academica de Ing. Electrica, Universidad Autonoma de Zacatecas, Apdo. Postal 336, 98000 Zacatecas, Zac. (Mexico)
2006-04-15
An artificial neural network has been designed to obtain neutron spectra from Bonner spheres spectrometer count rates. The neural network was trained using 129 neutron spectra. These include spectra from isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra based on mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. The re-binned spectra and the UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and their respective spectra were used as output during the neural network training. After training, the network was tested with the Bonner spheres count rates produced by folding a set of neutron spectra with the response matrix. This set contains data used during network training as well as data not used. Training and testing was carried out using the Matlab{sup (R)} program. To verify the network unfolding performance, the original and unfolded spectra were compared using the root mean square error. The use of artificial neural networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated with this ill-conditioned problem.
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
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.
Medical Text Classification using Convolutional Neural Networks
Hughes, Mark; Li, Irene; Kotoulas, Spyros; Suzumura, Toyotaro
2017-01-01
We present an approach to automatically classify clinical text at a sentence level. We are using deep convolutional neural networks to represent complex features. We train the network on a dataset providing a broad categorization of health information. Through a detailed evaluation, we demonstrate that our method outperforms several approaches widely used in natural language processing tasks by about 15%.
Medical Text Classification Using Convolutional Neural Networks.
Hughes, Mark; Li, Irene; Kotoulas, Spyros; Suzumura, Toyotaro
2017-01-01
We present an approach to automatically classify clinical text at a sentence level. We are using deep convolutional neural networks to represent complex features. We train the network on a dataset providing a broad categorization of health information. Through a detailed evaluation, we demonstrate that our method outperforms several approaches widely used in natural language processing tasks by about 15%.
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…
Abrahart, R. J.; Dawson, C. W.; Heppenstall, A. J.; See, L. M.
2009-04-01
The most critical issue in developing a neural network model is generalisation: how well will the preferred solution perform when it is applied to unseen datasets? The reported experiments used far-reaching sequences of model architectures and training periods to investigate the potential damage that could result from the impact of several interrelated items: (i) over-fitting - a machine learning concept related to exceeding some optimal architectural size; (ii) over-training - a machine learning concept related to the amount of adjustment that is applied to a specific model - based on the understanding that too much fine-tuning might result in a model that had accommodated random aspects of its training dataset - items that had no causal relationship to the target function; and (iii) over-parameterisation - a statistical modelling concept that is used to restrict the number of parameters in a model so as to match the information content of its calibration dataset. The last item in this triplet stems from an understanding that excessive computational complexities might permit an absurd and false solution to be fitted to the available material. Numerous feedforward multilayered perceptrons were trialled and tested. Two different methods of model construction were also compared and contrasted: (i) traditional Backpropagation of Error; and (ii) state-of-the-art Symbiotic Adaptive Neuro-Evolution. Modelling solutions were developed using the reported experimental set ups of Gaume & Gosset (2003). The models were applied to a near-linear hydrological modelling scenario in which past upstream and past downstream discharge records were used to forecast current discharge at the downstream gauging station [CS1: River Marne]; and a non-linear hydrological modelling scenario in which past river discharge measurements and past local meteorological records (precipitation and evaporation) were used to forecast current discharge at the river gauging station [CS2: Le Sauzay].
Yang, Xin; Liu, Chaoyue; Wang, Zhiwei; Yang, Jun; Min, Hung Le; Wang, Liang; Cheng, Kwang-Ting Tim
2017-12-01
Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive
van den Bergh, Jarrett; Schutz, Joey; Li, Alan; Chirayath, Ved
2017-01-01
NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Nets convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign. Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users input against pre-classified coral imagery to gauge their accuracy and utilize in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.
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.
Directory of Open Access Journals (Sweden)
Gavin Robertson
2011-01-01
Full Text Available Diabetes mellitus is a major, and increasing, global problem. However, it has been shown that, through good management of blood glucose levels (BGLs, the associated and costly complications can be reduced significantly. In this pilot study, Elman recurrent artificial neural networks (ANNs were used to make BGL predictions based on a history of BGLs, meal intake, and insulin injections. Twenty-eight datasets (from a single case scenario were compiled from the freeware mathematical diabetes simulator, AIDA. It was found that the most accurate predictions were made during the nocturnal period of the 24 hour daily cycle. The accuracy of the nocturnal predictions was measured as the root mean square error over five test days (RMSE5 day not used during ANN training. For BGL predictions of up to 1 hour a RMSE5 day of (±SD 0.15±0.04 mmol/L was observed. For BGL predictions up to 10 hours, a RMSE5 day of (±SD 0.14±0.16 mmol/L was observed. Future research will investigate a wider range of AIDA case scenarios, real-patient data, and data relating to other factors influencing BGLs. ANN paradigms based on real-time recurrent learning will also be explored to accommodate dynamic physiology in diabetes.
Directory of Open Access Journals (Sweden)
Jingbo Chen
2018-02-01
Full Text Available Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs, have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable.
Wave transmission prediction of multilayer floating breakwater using neural network
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Patil, S.G.; Hegde, A.V.
in unison to solve a specific problem. The network learns through examples, so it requires good examples to train properly and further a trained network model can be used for prediction purpose. Proceedings of ICOE 2009 Wave transmission... prediction of multilayer floating breakwater using neural network 577 In order to allow the network to learn both non-linear and linear relationships between input nodes and output nodes, multiple-layer neural networks are often used...
Neural network topology design for nonlinear control
Haecker, Jens; Rudolph, Stephan
2001-03-01
Neural networks, especially in nonlinear system identification and control applications, are typically considered to be black-boxes which are difficult to analyze and understand mathematically. Due to this reason, an in- depth mathematical analysis offering insight into the different neural network transformation layers based on a theoretical transformation scheme is desired, but up to now neither available nor known. In previous works it has been shown how proven engineering methods such as dimensional analysis and the Laplace transform may be used to construct a neural controller topology for time-invariant systems. Using the knowledge of neural correspondences of these two classical methods, the internal nodes of the network could also be successfully interpreted after training. As further extension to these works, the paper describes the latest of a theoretical interpretation framework describing the neural network transformation sequences in nonlinear system identification and control. This can be achieved By incorporation of the method of exact input-output linearization in the above mentioned two transform sequences of dimensional analysis and the Laplace transformation. Based on these three theoretical considerations neural network topologies may be designed in special situations by pure translation in the sense of a structural compilation of the known classical solutions into their correspondent neural topology. Based on known exemplary results, the paper synthesizes the proposed approach into the visionary goals of a structural compiler for neural networks. This structural compiler for neural networks is intended to automatically convert classical control formulations into their equivalent neural network structure based on the principles of equivalence between formula and operator, and operator and structure which are discussed in detail in this work.
[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.
Bayesian regularization of neural networks.
Burden, Frank; Winkler, Dave
2008-01-01
Bayesian regularized artificial neural networks (BRANNs) are more robust than standard back-propagation nets and can reduce or eliminate the need for lengthy cross-validation. Bayesian regularization is a mathematical process that converts a nonlinear regression into a "well-posed" statistical problem in the manner of a ridge regression. The advantage of BRANNs is that the models are robust and the validation process, which scales as O(N2) in normal regression methods, such as back propagation, is unnecessary. These networks provide solutions to a number of problems that arise in QSAR modeling, such as choice of model, robustness of model, choice of validation set, size of validation effort, and optimization of network architecture. They are difficult to overtrain, since evidence procedures provide an objective Bayesian criterion for stopping training. They are also difficult to overfit, because the BRANN calculates and trains on a number of effective network parameters or weights, effectively turning off those that are not relevant. This effective number is usually considerably smaller than the number of weights in a standard fully connected back-propagation neural net. Automatic relevance determination (ARD) of the input variables can be used with BRANNs, and this allows the network to "estimate" the importance of each input. The ARD method ensures that irrelevant or highly correlated indices used in the modeling are neglected as well as showing which are the most important variables for modeling the activity data. This chapter outlines the equations that define the BRANN method plus a flowchart for producing a BRANN-QSAR model. Some results of the use of BRANNs on a number of data sets are illustrated and compared with other linear and nonlinear models.
PREDIKSI FOREX MENGGUNAKAN MODEL NEURAL NETWORK
Directory of Open Access Journals (Sweden)
R. Hadapiningradja Kusumodestoni
2015-11-01
Full Text Available ABSTRAK Prediksi adalah salah satu teknik yang paling penting dalam menjalankan bisnis forex. Keputusan dalam memprediksi adalah sangatlah penting, karena dengan prediksi dapat membantu mengetahui nilai forex di waktu tertentu kedepan sehingga dapat mengurangi resiko kerugian. Tujuan dari penelitian ini dimaksudkan memprediksi bisnis fores menggunakan model neural network dengan data time series per 1 menit untuk mengetahui nilai akurasi prediksi sehingga dapat mengurangi resiko dalam menjalankan bisnis forex. Metode penelitian pada penelitian ini meliputi metode pengumpulan data kemudian dilanjutkan ke metode training, learning, testing menggunakan neural network. Setelah di evaluasi hasil penelitian ini menunjukan bahwa penerapan algoritma Neural Network mampu untuk memprediksi forex dengan tingkat akurasi prediksi 0.431 +/- 0.096 sehingga dengan prediksi ini dapat membantu mengurangi resiko dalam menjalankan bisnis forex. Kata kunci: prediksi, forex, neural network.
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.
Neural network optimization, components, and design selection
Weller, Scott W.
1990-07-01
Neural Networks are part of a revived technology which has received a lot of hype in recent years. As is apt to happen in any hyped technology, jargon and predictions make its assimilation and application difficult. Nevertheless, Neural Networks have found use in a number of areas, working on non-trivial and noncontrived problems. For example, one net has been trained to "read", translating English text into phoneme sequences. Other applications of Neural Networks include data base manipulation and the solving of muting and classification types of optimization problems. Neural Networks are constructed from neurons, which in electronics or software attempt to model but are not constrained by the real thing, i.e., neurons in our gray matter. Neurons are simple processing units connected to many other neurons over pathways which modify the incoming signals. A single synthetic neuron typically sums its weighted inputs, runs this sum through a non-linear function, and produces an output. In the brain, neurons are connected in a complex topology: in hardware/software the topology is typically much simpler, with neurons lying side by side, forming layers of neurons which connect to the layer of neurons which receive their outputs. This simplistic model is much easier to construct than the real thing, and yet can solve real problems. The information in a network, or its "memory", is completely contained in the weights on the connections from one neuron to another. Establishing these weights is called "training" the network. Some networks are trained by design -- once constructed no further learning takes place. Other types of networks require iterative training once wired up, but are not trainable once taught Still other types of networks can continue to learn after initial construction. The main benefit to using Neural Networks is their ability to work with conflicting or incomplete ("fuzzy") data sets. This ability and its usefulness will become evident in the following
Artificial Neural Network Modeling of an Inverse Fluidized Bed ...
African Journals Online (AJOL)
MICHAEL
modeling of the inverse fluidized bed reactor. In the proposed model, the trained neural network represents the kinetics of biological decomposition of pollutants in the reactor. The neural network has been trained with experimental data obtained from an inverse fluidized bed reactor treating the starch industry wastewater.
Nikelshpur, Dmitry O.
2014-01-01
Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…
Lee, Jun-Ki; Kwon, Yongju
2012-01-01
Fourteen science high school students participated in this study, which investigated neural-network plasticity associated with hypothesis-generating and hypothesis-understanding in learning. The students were divided into two groups and participated in either hypothesis-generating or hypothesis-understanding type learning programs, which were…
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...
Radio Signal Augmentation for Improved Training of a Convolutional Neural Network
2016-09-01
input. The CNN is trained using our technique of dataset augmentation, which applies a transformation specific to the sensory domain of radio (and...10 v Figures 1. Effect of receiver frequency error on samples representing a PSK modulation symbol. .......... 1 2. Basic CNN architecture for...classify features of interest in sensory input data. The most common input data is imagery, audio, and text data, with the output providing a descriptive
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.
Pap-smear Classification Using Efficient Second Order Neural Network Training Algorithms
DEFF Research Database (Denmark)
Ampazis, Nikolaos; Dounias, George; Jantzen, Jan
2004-01-01
. The algorithms are methodologically similar, and are based on iterations of the form employed in the Levenberg-Marquardt (LM) method for non-linear least squares problems with the inclusion of an additional adaptive momentum term arising from the formulation of the training task as a constrained optimization...... problem. The classification results obtained from the application of the algorithms on a standard benchmark pap-smear data set reveal the power of the two methods to obtain excellent solutions in difficult classification problems whereas other standard computational intelligence techniques achieve...
Training and evaluation of neural networks for multi-variate time series processing
DEFF Research Database (Denmark)
Fog, Torben L.; Larsen, Jan; Hansen, Lars Kai
1995-01-01
We study the training and generalization for multi-variate time series processing. It is suggested to used a quasi-maximum likelihood approach rather than the standard sum of squared errors, thus taking dependencies among the errors of the individual time series into account. This may lead...... to improved generalization performance. Further, we extend the optimal brain damage pruning technique to the multi-variate case. A key ingredient is an algebraic expression for the generalization ability of a multi-variate model. The variability of the suggested techniques are successfully demonstrated...
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...
Particle swarm optimization of a neural network model in a ...
Indian Academy of Sciences (India)
This paper presents a particle swarm optimization (PSO) technique to train an artificial neural network (ANN) for prediction of flank wear in drilling, and compares the network performance with that of the back propagation neural network (BPNN). This analysis is carried out following a series of experiments employing high ...
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...... 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...... Kalmann filter) representing state space description. The potentials of neural networks for control of non-linear processes are also examined, focusing on three different groups of control concepts, all considered as generalizations of known linear control concepts to handle also non-linear processes...
Evolutionary Algorithms For Neural Networks Binary And Real Data Classification
Directory of Open Access Journals (Sweden)
Dr. Hanan A.R. Akkar
2015-08-01
Full Text Available Artificial neural networks are complex networks emulating the way human rational neurons process data. They have been widely used generally in prediction clustering classification and association. The training algorithms that used to determine the network weights are almost the most important factor that influence the neural networks performance. Recently many meta-heuristic and Evolutionary algorithms are employed to optimize neural networks weights to achieve better neural performance. This paper aims to use recently proposed algorithms for optimizing neural networks weights comparing these algorithms performance with other classical meta-heuristic algorithms used for the same purpose. However to evaluate the performance of such algorithms for training neural networks we examine such algorithms to classify four opposite binary XOR clusters and classification of continuous real data sets such as Iris and Ecoli.
Advances in Artificial Neural Networks – Methodological Development and Application
Directory of Open Access Journals (Sweden)
Yanbo Huang
2009-08-01
Full Text Available 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 networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological
An Optoelectronic Neural Network
Neil, Mark A. A.; White, Ian H.; Carroll, John E.
1990-02-01
We describe and present results of an optoelectronic neural network processing system. The system uses an algorithm based on the Hebbian learning rule to memorise a set of associated vector pairs. Recall occurs by the processing of the input vector with these stored associations in an incoherent optical vector multiplier using optical polarisation rotating liquid crystal spatial light modulators to store the vectors and an optical polarisation shadow casting technique to perform multiplications. Results are detected on a photodiode array and thresholded electronically by a controlling microcomputer. The processor is shown to work in autoassociative and heteroassociative modes with up to 10 stored memory vectors of length 64 (equivalent to 64 neurons) and a cycle time of 50ms. We discuss the limiting factors at work in this system, how they affect its scalability and the general applicability of its principles to other systems.
Parameter estimation using compensatory neural networks
Indian Academy of Sciences (India)
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 ...
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...
Fast Fingerprint Classification with Deep Neural Network
DEFF Research Database (Denmark)
Michelsanti, Daniel; Guichi, Yanis; Ene, Andreea-Daniela
2017-01-01
. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage....
An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures
Energy Technology Data Exchange (ETDEWEB)
Schuman, Catherine D [ORNL; Plank, James [University of Tennessee (UT); Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)
2016-01-01
As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.
Czyzowska-Wisniewski, E. H.; Van Leeuwen, W. J. D.; Marsh, S. E.; Hirschboeck, K. K.; Wisniewski, W. T.
2014-12-01
Accurate estimation of Fractional Snow Cover (FSC) in complex alpine-forested terrain is now possible with appropriate remote sensing data and analysis techniques. This research examines what minimum combination of input variables are required to obtain state-of-the-art FSC estimates for heterogeneous alpine-forested terrains. Currently, one of the most accurate FSC estimators for alpine regions is based on training an Artificial Neural Network (ANN) that can deconvolve the relationships between numerous compounded and possibly non-linear bio-geophysical relations encountered in rugged terrain. Under the assumption that the ANN optimally extracts available information from its input data, we can exploit the ANN as a tool to assess the contributions toward FSC estimation of each of the data sources, and combinations thereof. By assessing the quality of the modeled FSC estimates versus ground equivalent data, suitable combinations of input variables can be identified. High spatial resolution imagery from IKONOS are used to estimate snow cover for ANN training and validation, and also for error assessment of the ANN FSC results. Input variables are initially chosen representing information already incorporated into leading snow cover estimators. Additional variables such as topographic slope, aspect, and shadow distribution are evaluated to observe the ANN as it accounts for illumination incidence and directional reflectance of surfaces affecting the viewed radiance in complex terrain. Snow usually covers vegetation and underlying geology partially, therefore the ANN also has to resolve spectral mixtures of unobscured surfaces surrounded by snow. Multispectral imagery if therefore acquired in the fall prior to the first snow of the season and are included in the ANN analyses for assessing the baseline reflectance values of the environment that later become modified by the snow. The best ANN FSC model performance was achieved when all 15 pre-selected inputs were used
NeMO-Net: The Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment
Chirayath, Ved
2017-01-01
In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8 percent error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets. We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Pythons extensive libraries for machine learning, as well as extending integration
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.
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.
Collision avoidance using neural networks
Sugathan, Shilpa; Sowmya Shree, B. V.; Warrier, Mithila R.; Vidhyapathi, C. M.
2017-11-01
Now a days, accidents on roads are caused due to the negligence of drivers and pedestrians or due to unexpected obstacles that come into the vehicle’s path. In this paper, a model (robot) is developed to assist drivers for a smooth travel without accidents. It reacts to the real time obstacles on the four critical sides of the vehicle and takes necessary action. The sensor used for detecting the obstacle was an IR proximity sensor. A single layer perceptron neural network is used to train and test all possible combinations of sensors result by using Matlab (offline). A microcontroller (ARM Cortex-M3 LPC1768) is used to control the vehicle through the output data which is received from Matlab via serial communication. Hence, the vehicle becomes capable of reacting to any combination of real time obstacles.
Yashchenko, Vitaliy A.
2000-03-01
On the basis of the analysis of scientific ideas reflecting the law in the structure and functioning the biological structures of a brain, and analysis and synthesis of knowledge, developed by various directions in Computer Science, also there were developed the bases of the theory of a new class neural-like growing networks, not having the analogue in world practice. In a base of neural-like growing networks the synthesis of knowledge developed by classical theories - semantic and neural of networks is. The first of them enable to form sense, as objects and connections between them in accordance with construction of the network. With thus each sense gets a separate a component of a network as top, connected to other tops. In common it quite corresponds to structure reflected in a brain, where each obvious concept is presented by certain structure and has designating symbol. Secondly, this network gets increased semantic clearness at the expense owing to formation not only connections between neural by elements, but also themselves of elements as such, i.e. here has a place not simply construction of a network by accommodation sense structures in environment neural of elements, and purely creation of most this environment, as of an equivalent of environment of memory. Thus neural-like growing networks are represented by the convenient apparatus for modeling of mechanisms of teleological thinking, as a fulfillment of certain psychophysiological of functions.
Pixel-wise Segmentation of Street with Neural Networks
Bittel, Sebastian; Kaiser, Vitali; Teichmann, Marvin; Thoma, Martin
2015-01-01
Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an $F_1$-score of 89.5% with a simple feedforward neural network which trained to solve a regression task.
Application of a neural network for reflectance spectrum classification
Yang, Gefei; Gartley, Michael
2017-05-01
Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.
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.
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.
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.
Flexible body control using neural networks
Mccullough, Claire L.
1992-01-01
Progress is reported on the control of Control Structures Interaction suitcase demonstrator (a flexible structure) using neural networks and fuzzy logic. It is concluded that while control by neural nets alone (i.e., allowing the net to design a controller with no human intervention) has yielded less than optimal results, the neural net trained to emulate the existing fuzzy logic controller does produce acceptible system responses for the initial conditions examined. Also, a neural net was found to be very successful in performing the emulation step necessary for the anticipatory fuzzy controller for the CSI suitcase demonstrator. The fuzzy neural hybrid, which exhibits good robustness and noise rejection properties, shows promise as a controller for practical flexible systems, and should be further evaluated.
Neural Network and Letter Recognition.
Lee, Hue Yeon
Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C -layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the 'Gabor' transform. Pattern dependent choice of center and wavelengths of 'Gabor' filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets. The correct recognition rate of the system increases with the number of training sets and eventually saturates at a certain value. Similar recognition rates are obtained for the above three different learning algorithms. The minimum error
Indian Academy of Sciences (India)
differences between biological neural networks (BNNs) of the brain and ANN s. A thorough understanding of ... neurons. Artificial neural models are loosely based on biology since a complete understanding of the .... A learning scheme for updating a neuron's connections (weights) was proposed by Donald Hebb in 1949.
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...
Memristor-based neural networks
Thomas, Andy
2013-03-01
The synapse is a crucial element in biological neural networks, but a simple electronic equivalent has been absent. This complicates the development of hardware that imitates biological architectures in the nervous system. Now, the recent progress in the experimental realization of memristive devices has renewed interest in artificial neural networks. The resistance of a memristive system depends on its past states and exactly this functionality can be used to mimic the synaptic connections in a (human) brain. After a short introduction to memristors, we present and explain the relevant mechanisms in a biological neural network, such as long-term potentiation and spike time-dependent plasticity, and determine the minimal requirements for an artificial neural network. We review the implementations of these processes using basic electric circuits and more complex mechanisms that either imitate biological systems or could act as a model system for them.
Pansharpening by Convolutional Neural Networks
National Research Council Canada - National Science Library
Masi, Giuseppe; Cozzolino, Davide; Verdoliva, Luisa; Scarpa, Giuseppe
2016-01-01
A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem...
Obstacle avoidance for power wheelchair using bayesian neural network.
Trieu, Hoang T; Nguyen, Hung T; Willey, Keith
2007-01-01
In this paper we present a real-time obstacle avoidance algorithm using a Bayesian neural network for a laser based wheelchair system. The raw laser data is modified to accommodate the wheelchair dimensions, allowing the free-space to be determined accurately in real-time. Data acquisition is performed to collect the patterns required for training the neural network. A Bayesian frame work is applied to determine the optimal neural network structure for the training data. This neural network is trained under the supervision of the Bayesian rule and the obstacle avoidance task is then implemented for the wheelchair system. Initial results suggest this approach provides an effective solution for autonomous tasks, suggesting Bayesian neural networks may be useful for wider assistive technology applications.
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...
Biologically Inspired Modular Neural Networks
Azam, Farooq
2000-01-01
This dissertation explores the modular learning in artificial neural networks that mainly driven by the inspiration from the neurobiological basis of the human learning. The presented modularization approaches to the neural network design and learning are inspired by the engineering, complexity, psychological and neurobiological aspects. The main theme of this dissertation is to explore the organization and functioning of the brain to discover new structural and learning ...
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 Network Based Load Frequency Control for Restructuring ...
African Journals Online (AJOL)
Electric load variations can happen independently in both units. Both neural controllers are trained with the back propagation-through-time algorithm. Use of a neural network to model the dynamic system is avoided by introducing the Jacobian matrices of the system in the back propagation chain used in controller training.
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
Artificial neural networks for prediction of percentage of water ...
Indian Academy of Sciences (India)
According to these input parameters, in the neural networks model, the percentage of water absorption of each specimen was predicted. The training and testing results in the neural networks model have shown a strong potential for predicting the percentage of water absorption of the geopolymer specimens.
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.
Decoding small surface codes with feedforward neural networks
Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen
2018-01-01
Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.
Optical-Correlator Neural Network Based On Neocognitron
Chao, Tien-Hsin; Stoner, William W.
1994-01-01
Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.
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...
Automated Modeling of Microwave Structures by Enhanced Neural Networks
Directory of Open Access Journals (Sweden)
Z. Raida
2006-12-01
Full Text Available The paper describes the methodology of the automated creation of neural models of microwave structures. During the creation process, artificial neural networks are trained using the combination of the particle swarm optimization and the quasi-Newton method to avoid critical training problems of the conventional neural nets. In the paper, neural networks are used to approximate the behavior of a planar microwave filter (moment method, Zeland IE3D. In order to evaluate the efficiency of neural modeling, global optimizations are performed using numerical models and neural ones. Both approaches are compared from the viewpoint of CPU-time demands and the accuracy. Considering conclusions, methodological recommendations for including neural networks to the microwave design are formulated.
Memory-optimal neural network approximation
Bölcskei, Helmut; Grohs, Philipp; Kutyniok, Gitta; Petersen, Philipp
2017-08-01
We summarize the main results of a recent theory-developed by the authors-establishing fundamental lower bounds on the connectivity and memory requirements of deep neural networks as a function of the complexity of the function class to be approximated by the network. These bounds are shown to be achievable. Specifically, all function classes that are optimally approximated by a general class of representation systems-so-called affine systems-can be approximated by deep neural networks with minimal connectivity and memory requirements. Affine systems encompass a wealth of representation systems from applied harmonic analysis such as wavelets, shearlets, ridgelets, α-shearlets, and more generally α-molecules. This result elucidates a remarkable universality property of deep neural networks and shows that they achieve the optimum approximation properties of all affine systems combined. Finally, we present numerical experiments demonstrating that the standard stochastic gradient descent algorithm generates deep neural networks which provide close-to-optimal approximation rates at minimal connectivity. Moreover, stochastic gradient descent is found to actually learn approximations that are sparse in the representation system optimally sparsifying the function class the network is trained on.
Neural networks for sign language translation
Wilson, Beth J.; Anspach, Gretel
1993-09-01
A neural network is used to extract relevant features of sign language from video images of a person communicating in American Sign Language or Signed English. The key features are hand motion, hand location with respect to the body, and handshape. A modular hybrid design is under way to apply various techniques, including neural networks, in the development of a translation system that will facilitate communication between deaf and hearing people. One of the neural networks described here is used to classify video images of handshapes into their linguistic counterpart in American Sign Language. The video image is preprocessed to yield Fourier descriptors that encode the shape of the hand silhouette. These descriptors are then used as inputs to a neural network that classifies their shapes. The network is trained with various examples from different signers and is tested with new images from new signers. The results have shown that for coarse handshape classes, the network is invariant to the type of camera used to film the various signers and to the segmentation technique.
Permeability prediction in shale gas reservoirs using Neural Network
Aliouane, Leila; Ouadfeul, Sid-Ali
2017-04-01
Here, we suggest the use of the artificial neural network for permeability prediction in shale gas reservoirs using artificial neural network. Prediction of Permeability in shale gas reservoirs is a complicated task that requires new models where Darcy's fluid flow model is not suitable. Proposed idea is based on the training of neural network machine using the set of well-logs data as an input and the measured permeability as an output. In this case the Multilayer Perceptron neural network machines is used with Levenberg Marquardt algorithm. Application to two horizontal wells drilled in the Barnett shale formation exhibit the power of neural network model to resolve such as problem. Keywords: Artificial neural network, permeability, prediction , shale gas.
Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.
Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu
2017-10-01
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.
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)
Energy Technology Data Exchange (ETDEWEB)
Hernandez P, C. F.; Martinez B, M. R.; Leon P, A. A.; Espinoza G, J. G.; Castaneda M, V. H.; Solis S, L. O.; Castaneda M, R.; Ortiz R, M.; Vega C, H. R. [Universidad Autonoma de Zacatecas, Av. Ramon Lopez Velarde 801, Col. Centro, 98000 Zacatecas, Zac. (Mexico); Mendez V, R. [Centro de Investigaciones Energeticas, Medioambientales y Tecnologicas, Laboratorio de Patrones Neutronicos, Av. Complutense 22, 28040 Madrid (Spain); Gallego, E. [Universidad Politecnica de Madrid, Departamento de Ingenieria Nuclear, ETSI Industriales, Jose Gutierrez Abascal 2, 28006 Madrid (Spain); De Sousa L, M. A. [Centro de Desenvolvimento da Tecnologia Nuclear / CNEN, Av. Pte. Antonio Carlos 6627, 31270-901 Pampulha, Belo Horizonte, Minas Gerais (Brazil)
2016-10-15
Neutron dosimetry is of great importance in radiation protection as aims to provide dosimetric quantities to assess the magnitude of detrimental health effects due to exposure of neutron radiation. To quantify detriment to health is necessary to evaluate the dose received by the occupationally exposed personnel using different detection systems called dosimeters, which have very dependent responses to the energy distribution of neutrons. The neutron detection is a much more complex problem than the detection of charged particles, since it does not carry an electric charge, does not cause direct ionization and has a greater penetration power giving the possibility of interacting with matter in a different way. Because of this, various neutron detection systems have been developed, among which the Bonner spheres spectrometric system stands out due to the advantages that possesses, such as a wide range of energy, high sensitivity and easy operation. However, once obtained the counting rates, the problem lies in the neutron spectrum deconvolution, necessary for the calculation of the doses, using different mathematical methods such as Monte Carlo, maximum entropy, iterative methods among others, which present various difficulties that have motivated the development of new technologies. Nowadays, methods based on artificial intelligence technologies are being used to perform neutron dosimetry, mainly using the theory of artificial neural networks. In these new methods the need for spectrum reconstruction can be eliminated for the calculation of the doses. In this work an artificial neural network or reverse propagation was trained for the calculation of 15 equivalent doses from the counting rates of the Bonner spheres spectrometric system using a set of 7 spheres, one of 2 spheres and two of a single sphere of different sizes, testing different error values until finding the most appropriate. The optimum network topology was obtained through the robust design
Spiking modular neural networks: A neural network modeling approach for hydrological processes
National Research Council Canada - National Science Library
Kamban Parasuraman; Amin Elshorbagy; Sean K. Carey
2006-01-01
.... In this study, a novel neural network model called the spiking modular neural networks (SMNNs) is proposed. An SMNN consists of an input layer, a spiking layer, and an associator neural network layer...
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.
Directory of Open Access Journals (Sweden)
Nemesio J. Rodríguez-Fernández
2016-11-01
Full Text Available A method to retrieve soil moisture (SM from Advanced Scanning Microwave Radiometer—Earth Observing System Sensor (AMSR-E observations using Soil Moisture and Ocean Salinity (SMOS Level 3 SM as a reference is discussed. The goal is to obtain longer time series of SM with no significant bias and with a similar dynamical range to that of the SMOS SM dataset. This method consists of training a neural network (NN to obtain a global non-linear relationship linking AMSR-E brightness temperatures ( T b to the SMOS L3 SM dataset on the concurrent mission period of 1.5 years. Then, the NN model is used to derive soil moisture from past AMSR-E observations. It is shown that in spite of the different frequencies and sensing depths of AMSR-E and SMOS, it is possible to find such a global relationship. The sensitivity of AMSR-E T b ’s to soil temperature ( T s o i l was also evaluated using European Centre for Medium-Range Weather Forecast Interim/Land re-analysis (ERA-Land and Modern-Era Retrospective analysis for Research and Applications-Land (MERRA-Land model data. The best combination of AMSR-E T b ’s to retrieve T s o i l is H polarization at 23 and 36 GHz plus V polarization at 36 GHz. Regarding SM, several combinations of input data show a similar performance in retrieving SM. One NN that uses C and X bands and T s o i l information was chosen to obtain SM in the 2003–2011 period. The new dataset shows a low bias (<0.02 m3/m3 and low standard deviation of the difference (<0.04 m3/m3 with respect to SMOS L3 SM over most of the globe’s surface. The new dataset was evaluated together with other AMSR-E SM datasets and the Climate Change Initiative (CCI SM dataset against the MERRA-Land and ERA-Land models for the 2003–2011 period. All datasets show a significant bias with respect to models for boreal regions and high correlations over regions other than the tropical and boreal forest. All of the global SM datasets including AMSR-E NN were also
Cicero, Mark; Bilbily, Alexander; Colak, Errol; Dowdell, Tim; Gray, Bruce; Perampaladas, Kuhan; Barfett, Joseph
2017-05-01
Convolutional neural networks (CNNs) are a subtype of artificial neural network that have shown strong performance in computer vision tasks including image classification. To date, there has been limited application of CNNs to chest radiographs, the most frequently performed medical imaging study. We hypothesize CNNs can learn to classify frontal chest radiographs according to common findings from a sufficiently large data set. Our institution's research ethics board approved a single-center retrospective review of 35,038 adult posterior-anterior chest radiographs and final reports performed between 2005 and 2015 (56% men, average age of 56, patient type: 24% inpatient, 39% outpatient, 37% emergency department) with a waiver for informed consent. The GoogLeNet CNN was trained using 3 graphics processing units to automatically classify radiographs as normal (n = 11,702) or into 1 or more of cardiomegaly (n = 9240), consolidation (n = 6788), pleural effusion (n = 7786), pulmonary edema (n = 1286), or pneumothorax (n = 1299). The network's performance was evaluated using receiver operating curve analysis on a test set of 2443 radiographs with the criterion standard being board-certified radiologist interpretation. Using 256 × 256-pixel images as input, the network achieved an overall sensitivity and specificity of 91% with an area under the curve of 0.964 for classifying a study as normal (n = 1203). For the abnormal categories, the sensitivity, specificity, and area under the curve, respectively, were 91%, 91%, and 0.962 for pleural effusion (n = 782), 82%, 82%, and 0.868 for pulmonary edema (n = 356), 74%, 75%, and 0.850 for consolidation (n = 214), 81%, 80%, and 0.875 for cardiomegaly (n = 482), and 78%, 78%, and 0.861 for pneumothorax (n = 167). Current deep CNN architectures can be trained with modest-sized medical data sets to achieve clinically useful performance at detecting and excluding common pathology on chest radiographs.
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.
Multiprocessor Neural Network in Healthcare.
Godó, Zoltán Attila; Kiss, Gábor; Kocsis, Dénes
2015-01-01
A possible way of creating a multiprocessor artificial neural network is by the use of microcontrollers. The RISC processors' high performance and the large number of I/O ports mean they are greatly suitable for creating such a system. During our research, we wanted to see if it is possible to efficiently create interaction between the artifical neural network and the natural nervous system. To achieve as much analogy to the living nervous system as possible, we created a frequency-modulated analog connection between the units. Our system is connected to the living nervous system through 128 microelectrodes. Two-way communication is provided through A/D transformation, which is even capable of testing psychopharmacons. The microcontroller-based analog artificial neural network can play a great role in medical singal processing, such as ECG, EEG etc.
Convolutional Neural Networks for Font Classification
Tensmeyer, Chris; Saunders, Daniel; Martinez, Tony
2017-01-01
Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We present a simple framework based on Convolutional Neural Networks (CNNs), where a CNN is trained to classify small patches of text into predefined font classes. To classify page or line images, we average the CNN predictions over densely extracted patches. We show that this method achieves state-of-the-art performance...
A Dynamic Neural Network Approach to CBM
2011-03-15
Therefore post-processing is needed to extract the time difference between corresponding events from which to calculate the crankshaft rotational speed...potentially already available from existing sensors (such as a crankshaft timing device) and a Neural Network processor to carry out the calculation . As...files are designated with the “_genmod” suffix. These files were the sources for the training and testing sets and made the extraction process easy
Bos, M.; Weber, H.T.; Weber, H.T.
1991-01-01
Neural networks are shown to be useful as empirical mathematical models in the calculation of quantitative analytical results, giving sufficient accuracy to compete successfully with various common calibration procedures. The performance of these neural-network models for calibration data from x-ray
Inverse kinematics problem in robotics using neural networks
Choi, Benjamin B.; Lawrence, Charles
1992-01-01
In this paper, Multilayer Feedforward Networks are applied to the robot inverse kinematic problem. The networks are trained with endeffector position and joint angles. After training, performance is measured by having the network generate joint angles for arbitrary endeffector trajectories. A 3-degree-of-freedom (DOF) spatial manipulator is used for the study. It is found that neural networks provide a simple and effective way to both model the manipulator inverse kinematics and circumvent the problems associated with algorithmic solution methods.
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...
voltage compensation using artificial neural network
African Journals Online (AJOL)
Offor Theophilos
VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK: A CASE STUDY OF. RUMUOLA ... using artificial neural network (ANN) controller based dynamic voltage restorer (DVR). ... substation by simulating with sample of average voltage for Omerelu, Waterlines, Rumuola, Shell Industrial and Barracks.
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.
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.
Ship Benchmark Shaft and Engine Gain FDI Using Neural Network
DEFF Research Database (Denmark)
Bendtsen, Jan Dimon; Izadi-Zamanabadi, Roozbeh
2002-01-01
This paper concerns fault detection and isolation based on neural network modeling. A neural network is trained to recognize the input-output behavior of a nonlinear plant, and faults are detected if the output estimated by the network differs from the measured plant output by more than a specified...... threshold value. In the paper a method for determining this threshold based on the neural network model is proposed, which can be used for a design strategy to handle residual sensitivity to input variations. The proposed method is used for successful FDI of a diesel engine gain fault in a ship propulsion...
ESTIMATION OF PV MODULE SURFACE TEMPERATURE USING ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Can Coskun
2016-12-01
Full Text Available This study aimed to use the artificial neural network (ANN method to estimate the surface temperature of a photovoltaic (PV panel. Using the experimentally obtained PV data, the accuracy of the ANN model was evaluated. To train the artificial neural network (ANN, outer temperature solar radiation and wind speed values were inputs and surface temperature was an output. The ANN was used to estimate PV panel surface temperature. Using the Levenberg-Marquardt (LM algorithm the feed forward artificial neural network was trained. Two back propagation type ANN algorithms were used and their performance was compared with the estimate from the LM algorithm. To train the artificial neural network, experimental data were used for two thirds with the remaining third used for testing. Additionally scaled conjugate gradient (SCG back propagation and resilient back propagation (RB type ANN algorithms were used for comparison with the LM algorithm. The performances of these three types of artificial neural network were compared and mean error rates of between 0.005962 and 0.012177% were obtained. The best estimate was produced by the LM algorithm. Estimation of PV surface temperature with artificial neural networks provides better results than conventional correlation methods. This study showed that artificial neural networks may be effectively used to estimate PV surface temperature.
Analysis Resilient Algorithm on Artificial Neural Network Backpropagation
Saputra, Widodo; Tulus; Zarlis, Muhammad; Widia Sembiring, Rahmat; Hartama, Dedy
2017-12-01
Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.
Optoelectronic Implementation of Neural Networks
Indian Academy of Sciences (India)
Home; Journals; Resonance – Journal of Science Education; Volume 3; Issue 9. Optoelectronic Implementation of Neural Networks - Use of Optics in Computing. R Ramachandran. General Article Volume 3 Issue 9 September 1998 pp 45-55. Fulltext. Click here to view fulltext PDF. Permanent link:
Aphasia Classification Using Neural Networks
DEFF Research Database (Denmark)
Axer, H.; Jantzen, Jan; Berks, G.
2000-01-01
A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests...
Novel quantum inspired binary neural network algorithm
Indian Academy of Sciences (India)
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 ...
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.
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.
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).
UAV Trajectory Modeling Using Neural Networks
Xue, Min
2017-01-01
Massive small unmanned aerial vehicles are envisioned to operate in the near future. While there are lots of research problems need to be addressed before dense operations can happen, trajectory modeling remains as one of the keys to understand and develop policies, regulations, and requirements for safe and efficient unmanned aerial vehicle operations. The fidelity requirement of a small unmanned vehicle trajectory model is high because these vehicles are sensitive to winds due to their small size and low operational altitude. Both vehicle control systems and dynamic models are needed for trajectory modeling, which makes the modeling a great challenge, especially considering the fact that manufactures are not willing to share their control systems. This work proposed to use a neural network approach for modelling small unmanned vehicle's trajectory without knowing its control system and bypassing exhaustive efforts for aerodynamic parameter identification. As a proof of concept, instead of collecting data from flight tests, this work used the trajectory data generated by a mathematical vehicle model for training and testing the neural network. The results showed great promise because the trained neural network can predict 4D trajectories accurately, and prediction errors were less than 2:0 meters in both temporal and spatial dimensions.
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].
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...
Dynamic properties of cellular neural networks
Directory of Open Access Journals (Sweden)
Angela Slavova
1993-01-01
Full Text Available Dynamic behavior of a new class of information-processing systems called Cellular Neural Networks is investigated. In this paper we introduce a small parameter in the state equation of a cellular neural network and we seek for periodic phenomena. New approach is used for proving stability of a cellular neural network by constructing Lyapunov's majorizing equations. This algorithm is helpful for finding a map from initial continuous state space of a cellular neural network into discrete output. A comparison between cellular neural networks and cellular automata is made.
1993-07-01
algoritm . More sophisticated modifications of the algorithm have been developed which dc not suffer fron: long I training times for high-dimensional...then one is likely to have dark eyes" is the notion of j o0 imlcain A impie B sotad • )masta fAi rete stu.Ta PA PB PA-B 0 0 1 o 1 1 1 0 0 In other
Neural Networks through Shared Maps in Mobile Devices
Directory of Open Access Journals (Sweden)
William Raveane
2014-12-01
Full Text Available We introduce a hybrid system composed of a convolutional neural network and a discrete graphical model for image recognition. This system improves upon traditional sliding window techniques for analysis of an image larger than the training data by effectively processing the full input scene through the neural network in less time. The final result is then inferred from the neural network output through energy minimization to reach a more precize localization than what traditional maximum value class comparisons yield. These results are apt for applying this process in a mobile device for real time image recognition.
Autonomous Navigation Apparatus With Neural Network for a Mobile Vehicle
Quraishi, Naveed (Inventor)
1996-01-01
An autonomous navigation system for a mobile vehicle arranged to move within an environment includes a plurality of sensors arranged on the vehicle and at least one neural network including an input layer coupled to the sensors, a hidden layer coupled to the input layer, and an output layer coupled to the hidden layer. The neural network produces output signals representing respective positions of the vehicle, such as the X coordinate, the Y coordinate, and the angular orientation of the vehicle. A plurality of patch locations within the environment are used to train the neural networks to produce the correct outputs in response to the distances sensed.
UAV Trajectory Modeling Using Neural Networks
Xue, Min
2017-01-01
Large amount of small Unmanned Aerial Vehicles (sUAVs) are projected to operate in the near future. Potential sUAV applications include, but not limited to, search and rescue, inspection and surveillance, aerial photography and video, precision agriculture, and parcel delivery. sUAVs are expected to operate in the uncontrolled Class G airspace, which is at or below 500 feet above ground level (AGL), where many static and dynamic constraints exist, such as ground properties and terrains, restricted areas, various winds, manned helicopters, and conflict avoidance among sUAVs. How to enable safe, efficient, and massive sUAV operations at the low altitude airspace remains a great challenge. NASA's Unmanned aircraft system Traffic Management (UTM) research initiative works on establishing infrastructure and developing policies, requirement, and rules to enable safe and efficient sUAVs' operations. To achieve this goal, it is important to gain insights of future UTM traffic operations through simulations, where the accurate trajectory model plays an extremely important role. On the other hand, like what happens in current aviation development, trajectory modeling should also serve as the foundation for any advanced concepts and tools in UTM. Accurate models of sUAV dynamics and control systems are very important considering the requirement of the meter level precision in UTM operations. The vehicle dynamics are relatively easy to derive and model, however, vehicle control systems remain unknown as they are usually kept by manufactures as a part of intellectual properties. That brings challenges to trajectory modeling for sUAVs. How to model the vehicle's trajectories with unknown control system? This work proposes to use a neural network to model a vehicle's trajectory. The neural network is first trained to learn the vehicle's responses at numerous conditions. Once being fully trained, given current vehicle states, winds, and desired future trajectory, the neural
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.
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...
A constructive algorithm for unsupervised learning with incremental neural network
Wang, Jenq-Haur; Wang, Hsin-Yang; Chen, Yen-Lin; Liu, Chuan-Ming
2015-01-01
Artificial neural network (ANN) has wide applications such as data processing and classification. However, comparing with other classification methods, ANN needs enormous memory space and training time to build the model. This makes ANN infeasible in practical applications. In this paper, we try to integrate the ideas of human learning mechanism with the existing models of ANN. We propose an incremental neural network construction framework for unsupervised learning. In this framework, a neur...
On Extending Neural Networks with Loss Ensembles for Text Classification
Hajiabadi, Hamideh; Molla-Aliod, Diego; Monsefi, Reza
2017-01-01
Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a neural network extended with an ensemble loss function for text classification. The weight of each weak loss function is tuned within the training phase through the gradient propagation optimization method of the neural network. The approach is evaluated on...
Neural-Network Control Of Prosthetic And Robotic Hands
Buckley, Theresa M.
1991-01-01
Electronic neural networks proposed for use in controlling robotic and prosthetic hands and exoskeletal or glovelike electromechanical devices aiding intact but nonfunctional hands. Specific to patient, who activates grasping motion by voice command, by mechanical switch, or by myoelectric impulse. Patient retains higher-level control, while lower-level control provided by neural network analogous to that of miniature brain. During training, patient teaches miniature brain to perform specialized, anthropomorphic movements unique to himself or herself.
Deng, Lei; Jiao, Peng; Pei, Jing; Wu, Zhenzhi; Li, Guoqi
2018-02-02
Although deep neural networks (DNNs) are being a revolutionary power to open up the AI era, the notoriously huge hardware overhead has challenged their applications. Recently, several binary and ternary networks, in which the costly multiply-accumulate operations can be replaced by accumulations or even binary logic operations, make the on-chip training of DNNs quite promising. Therefore there is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discrete. The second one is how to remove the full-precision hidden weights in the training phase to break the bottlenecks of memory/computation consumption. To address the first issue, we present a multi-step neuronal activation discretization method and a derivative approximation technique that enable the implementing the back propagation algorithm on discrete DNNs. While for the second issue, we propose a discrete state transition (DST) methodology to constrain the weights in a discrete space without saving the hidden weights. Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github.com/AcrossV/Gated-XNOR. More particularly, we find that when both the weights and activations become ternary values, the DNNs can be reduced to sparse binary networks, termed as gated XNOR networks (GXNOR-Nets) since only the event of non-zero weight and non-zero activation enables the control gate to start the XNOR logic operations in the original binary networks. This promises the event-driven hardware design for efficient mobile intelligence. We achieve advanced performance compared with state-of-the-art algorithms. Furthermore, the computational sparsity
Energy Technology Data Exchange (ETDEWEB)
Martinez B, M.R.; Ortiz R, J.M.; Vega C, H.R. [UAZ, Av. Ramon Lopez Velarde No. 801, 98000 Zacatecas (Mexico)
2006-07-01
An Artificial Neural Network has been designed, trained and tested to unfold neutron spectra and simultaneously to calculate equivalent doses. A set of 187 neutron spectra compiled by the International Atomic Energy Agency and 13 equivalent doses were used in the artificial neural network designed, trained and tested. In order to design the neural network was used the robust design of artificial neural networks methodology, which assures that the quality of the neural networks takes into account from the design stage. Unless previous works, here, for first time a group of neural networks were designed and trained to unfold 187 neutron spectra and at the same time to calculate 13 equivalent doses, starting from the count rates coming from the Bonner spheres system by using a systematic and experimental strategy. (Author)
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.
Neural network design for J function approximation in dynamic programming
Pang, X
1998-01-01
This paper shows that a new type of artificial neural network (ANN) -- the Simultaneous Recurrent Network (SRN) -- can, if properly trained, solve a difficult function approximation problem which conventional ANNs -- either feedforward or Hebbian -- cannot. This problem, the problem of generalized maze navigation, is typical of problems which arise in building true intelligent control systems using neural networks. (Such systems are discussed in the chapter by Werbos in K.Pribram, Brain and Values, Erlbaum 1998.) The paper provides a general review of other types of recurrent networks and alternative training techniques, including a flowchart of the Error Critic training design, arguable the only plausible approach to explain how the brain adapts time-lagged recurrent systems in real-time. The C code of the test is appended. As in the first tests of backprop, the training here was slow, but there are ways to do better after more experience using this type of network.
Directory of Open Access Journals (Sweden)
Jiao-Hong Yi
2016-01-01
Full Text Available Probabilistic neural network has successfully solved all kinds of engineering problems in various fields since it is proposed. In probabilistic neural network, Spread has great influence on its performance, and probabilistic neural network will generate bad prediction results if it is improperly selected. It is difficult to select the optimal manually. In this article, a variant of probabilistic neural network with self-adaptive strategy, called self-adaptive probabilistic neural network, is proposed. In self-adaptive probabilistic neural network, Spread can be self-adaptively adjusted and selected and then the best selected Spread is used to guide the self-adaptive probabilistic neural network train and test. In addition, two simplified strategies are incorporated into the proposed self-adaptive probabilistic neural network with the aim of further improving its performance and then two versions of simplified self-adaptive probabilistic neural network (simplified self-adaptive probabilistic neural networks 1 and 2 are proposed. The variants of self-adaptive probabilistic neural networks are further applied to solve the transformer fault diagnosis problem. By comparing them with basic probabilistic neural network, and the traditional back propagation, extreme learning machine, general regression neural network, and self-adaptive extreme learning machine, the results have experimentally proven that self-adaptive probabilistic neural networks have a more accurate prediction and better generalization performance when addressing the transformer fault diagnosis problem.
Neural Network Machine Learning and Dimension Reduction for Data Visualization
Liles, Charles A.
2014-01-01
Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.
DEFF Research Database (Denmark)
Pedersen, Morten With
1997-01-01
Training recurrent networks is generally believed to be a difficult task. Excessive training times and lack of convergence to an acceptable solution are frequently reported. In this paper we seek to explain the reason for this from a numerical point of view and show how to avoid problems when...
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.
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.
An artificial neural network based fast radiative transfer model for ...
Indian Academy of Sciences (India)
In the present study, a fast radiative transfer model using neural networks is proposed to simulate radiances corresponding to the wavenumbers of INSAT-3D. Realistic atmospheric temperature and humidity profiles have been used for training the network. Spectral response functions of GOES-13, a satellite similar in ...
On-line backpropagation in two-layered neural networks
Riegler, Peter; Biehl, Michael
1995-01-01
We present an exact analysis of learning a rule by on-line gradient descent in a two-layered neural network with adjustable hidden-to-output weights (backpropagation of error). Results are compared with the training of networks having the same architecture but fixed weights in the second layer.
Quantum generalisation of feedforward neural networks
Wan, Kwok Ho; Dahlsten, Oscar; Kristjánsson, Hlér; Gardner, Robert; Kim, M. S.
2017-09-01
We propose a quantum generalisation of a classical neural network. The classical neurons are firstly rendered reversible by adding ancillary bits. Then they are generalised to being quantum reversible, i.e., unitary (the classical networks we generalise are called feedforward, and have step-function activation functions). The quantum network can be trained efficiently using gradient descent on a cost function to perform quantum generalisations of classical tasks. We demonstrate numerically that it can: (i) compress quantum states onto a minimal number of qubits, creating a quantum autoencoder, and (ii) discover quantum communication protocols such as teleportation. Our general recipe is theoretical and implementation-independent. The quantum neuron module can naturally be implemented photonically.
Ocean wave forecasting using recurrent neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Prabaharan, N.
to the biological neurons, works on the input and output passing through a hidden layer. The ANN used here is a data- oriented modeling technique to find relations between input and output patterns by self learning and without any fixed mathematical form assumed... = 1/p ? Ep (2) Where, Ep = ? ? (Tk ?Ok)2 (3) p is the total number of training patterns; Tk is the actual output and Ok is the predicted output at kth output node. In the learning process of backpropagation neural network...
Convolution neural networks for ship type recognition
Rainey, Katie; Reeder, John D.; Corelli, Alexander G.
2016-05-01
Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.
A hybrid training method for neural energy estimation in calorimetry
Da Silva, P V M; Seixas, J
2001-01-01
A neural mapping is developed to improve the overall performance of Tilecal, which is the hadronic calorimeter of the ATLAS detector. Feeding the input nodes of a multilayer feedforward neural network with the energy values sampled by the calorimeter cells in beam tests, it is shown that the original energy scale of pion beams is reconstructed over a wide energy range and linearity is significantly improved. As it happens for classical methods, a compromise between nonlinearity correction and the optimization of the energy resolution of the detector has to be accomplished. A hybrid training method for the neural mapping is proposed to achieve this design goal. Using the backpropagation algorithm, the method intercalates an epoch of training steps, for which the neural mapping mainly focus on linearity correction, with another block of training steps, in which the original energy resolution obtained by linearly combining the calorimeter cells becomes the main target. (6 refs).
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.
Energy Technology Data Exchange (ETDEWEB)
Ortiz R, J. M. [Escuela Politecnica Superior, Departamento de Electrotecnia y Electronica, Avda. Menendez Pidal s/n, Cordoba (Spain); Martinez B, M. R.; Vega C, H. R. [Universidad Autonoma de Zacatecas, Unidad Academica de Estudios Nucleares, Calle Cipres No. 10, Fracc. La Penuela, 98068 Zacatecas (Mexico); Gallego D, E.; Lorente F, A. [Universidad Politecnica de Madrid, Departamento de Ingenieria Nuclear, ETSI Industriales, C. Jose Gutierrez Abascal 2, 28006 Madrid (Spain); Mendez V, R.; Los Arcos M, J. M.; Guerrero A, J. E., E-mail: morvymm@yahoo.com.m [CIEMAT, Laboratorio de Metrologia de Radiaciones Ionizantes, Avda. Complutense 22, 28040 Madrid (Spain)
2011-02-15
With the Bonner spheres spectrometer neutron spectrum is obtained through an unfolding procedure. Monte Carlo methods, Regularization, Parametrization, Least-squares, and Maximum Entropy are some of the techniques utilized for unfolding. In the last decade methods based on Artificial Intelligence Technology have been used. Approaches based on Genetic Algorithms and Artificial Neural Networks (Ann) have been developed in order to overcome the drawbacks of previous techniques. Nevertheless the advantages of Ann still it has some drawbacks mainly in the design process of the network, vg the optimum selection of the architectural and learning Ann parameters. In recent years the use of hybrid technologies, combining Ann and genetic algorithms, has been utilized to. In this work, several Ann topologies were trained and tested using Ann and Genetically Evolved Artificial Neural Networks in the aim to unfold neutron spectra using the count rates of a Bonner sphere spectrometer. Here, a comparative study of both procedures has been carried out. (Author)
Reject mechanisms for massively parallel neural network character recognition systems
Garris, Michael D.; Wilson, Charles L.
1992-12-01
Two reject mechanisms are compared using a massively parallel character recognition system implemented at NIST. The recognition system was designed to study the feasibility of automatically recognizing hand-printed text in a loosely constrained environment. The first method is a simple scalar threshold on the output activation of the winning neurode from the character classifier network. The second method uses an additional neural network trained on all outputs from the character classifier network to accept or reject assigned classifications. The neural network rejection method was expected to perform with greater accuracy than the scalar threshold method, but this was not supported by the test results presented. The scalar threshold method, even though arbitrary, is shown to be a viable reject mechanism for use with neural network character classifiers. Upon studying the performance of the neural network rejection method, analyses show that the two neural networks, the character classifier network and the rejection network, perform very similarly. This can be explained by the strong non-linear function of the character classifier network which effectively removes most of the correlation between character accuracy and all activations other than the winning activation. This suggests that any effective rejection network must receive information from the system which has not been filtered through the non-linear classifier.
Marginalization in Random Nonlinear Neural Networks
Vasudeva Raju, Rajkumar; Pitkow, Xaq
2015-03-01
Computations involved in tasks like causal reasoning in the brain require a type of probabilistic inference known as marginalization. Marginalization corresponds to averaging over irrelevant variables to obtain the probability of the variables of interest. This is a fundamental operation that arises whenever input stimuli depend on several variables, but only some are task-relevant. Animals often exhibit behavior consistent with marginalizing over some variables, but the neural substrate of this computation is unknown. It has been previously shown (Beck et al. 2011) that marginalization can be performed optimally by a deterministic nonlinear network that implements a quadratic interaction of neural activity with divisive normalization. We show that a simpler network can perform essentially the same computation. These Random Nonlinear Networks (RNN) are feedforward networks with one hidden layer, sigmoidal activation functions, and normally-distributed weights connecting the input and hidden layers. We train the output weights connecting the hidden units to an output population, such that the output model accurately represents a desired marginal probability distribution without significant information loss compared to optimal marginalization. Simulations for the case of linear coordinate transformations show that the RNN model has good marginalization performance, except for highly uncertain inputs that have low amplitude population responses. Behavioral experiments, based on these results, could then be used to identify if this model does indeed explain how the brain performs marginalization.
Fuzzy neural networks: theory and applications
Gupta, Madan M.
1994-10-01
During recent years, significant advances have been made in two distinct technological areas: fuzzy logic and computational neural networks. The theory of fuzzy logic provides a mathematical framework to capture the uncertainties associated with human cognitive processes, such as thinking and reasoning. It also provides a mathematical morphology to emulate certain perceptual and linguistic attributes associated with human cognition. On the other hand, the computational neural network paradigms have evolved in the process of understanding the incredible learning and adaptive features of neuronal mechanisms inherent in certain biological species. Computational neural networks replicate, on a small scale, some of the computational operations observed in biological learning and adaptation. The integration of these two fields, fuzzy logic and neural networks, have given birth to an emerging technological field -- fuzzy neural networks. Fuzzy neural networks, have the potential to capture the benefits of these two fascinating fields, fuzzy logic and neural networks, into a single framework. The intent of this tutorial paper is to describe the basic notions of biological and computational neuronal morphologies, and to describe the principles and architectures of fuzzy neural networks. Towards this goal, we develop a fuzzy neural architecture based upon the notion of T-norm and T-conorm connectives. An error-based learning scheme is described for this neural structure.
Modeling Broadband Microwave Structures by Artificial Neural Networks
Directory of Open Access Journals (Sweden)
V. Otevrel
2004-06-01
Full Text Available The paper describes the exploitation of feed-forward neural networksand recurrent neural networks for replacing full-wave numerical modelsof microwave structures in complex microwave design tools. Building aneural model, attention is turned to the modeling accuracy and to theefficiency of building a model. Dealing with the accuracy, we describea method of increasing it by successive completing a training set.Neural models are mutually compared in order to highlight theiradvantages and disadvantages. As a reference model for comparisons,approximations based on standard cubic splines are used. Neural modelsare used to replace both the time-domain numeric models and thefrequency-domain ones.
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.
Neural Networks in Antennas and Microwaves: A Practical Approach
Directory of Open Access Journals (Sweden)
Z. Raida
2001-12-01
Full Text Available Neural networks are electronic systems which can be trained toremember behavior of a modeled structure in given operational points,and which can be used to approximate behavior of the structure out ofthe training points. These approximation abilities of neural nets aredemonstrated on modeling a frequency-selective surface, a microstriptransmission line and a microstrip dipole. Attention is turned to theaccuracy and to the efficiency of neural models. The association ofneural models and genetic algorithms, which can provide a global designtool, is discussed.
Estimation of concrete compressive strength using artificial neural network
Directory of Open Access Journals (Sweden)
Kostić Srđan
2015-01-01
Full Text Available 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 superplasticizer of melamine type. These specimens were exposed to different number of freeze/thaw cycles and their compressive strength was determined after 7, 20 and 32 days. The obtained results indicate that neural network with one hidden layer and twelve hidden nodes gives reasonable prediction accuracy in comparison to experimental results (R=0.965, MSE=0.005. These results of the performed analysis are further confirmed by calculating the standard statistical errors: the chosen architecture of neural network shows the smallest value of mean absolute percentage error (MAPE=, variance absolute relative error (VARE and median absolute error (MEDAE, and the highest value of variance accounted for (VAF.
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
Suzuki, Kenji; Shiraishi, Junji; Li, Feng; Abe, Hiroyuki; MacMahon, Heber; Doi, Kunio
2005-04-01
A major challenge in computer-aided diagnostic (CAD) schemes for nodule detection on chest radiographs is the detection of nodules that overlap with ribs. Our purpose was to develop a technique for false-positive reduction in a CAD scheme using a rib-suppression technique based on massive training artificial neural networks (MTANNs). We developed a multiple MTANN (multi-MTANN) consisting of eight MTANNs for removing eight types of false positives. For further removal of false positives caused by ribs, we developed a rib-suppression technique using a multi-resolution MTANN consisting of three different resolution MTANNs. To suppress the contrast of ribs, the multi-resolution MTANN was trained with input chest radiographs and the teaching soft-tissue images obtained by using a dual-energy subtraction technique. Our database consisted of 91 nodules in 91 chest radiographs. With our original CAD scheme based on a difference image technique with linear discriminant analysis, a sensitivity of 82.4% (75/91 nodules) with 4.5 (410/91) false positives per image was achieved. The trained multi-MTANN was able to remove 62.7% (257/410) of false positives with a loss of one true positive. With the rib-suppression technique, the contrast of ribs in chest radiographs was suppressed substantially. Due to the effect of rib-suppression, 41.2% (63/153) of the remaining false positives were removed without a loss of any true positives. Thus, the false-positive rate of our CAD scheme was improved substantially, while a high sensitivity was maintained.
Pansharpening by Convolutional Neural Networks
Directory of Open Access Journals (Sweden)
Giuseppe Masi
2016-07-01
Full Text Available A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.
Neural networks and perceptual learning
Tsodyks, Misha; Gilbert, Charles
2005-01-01
Sensory perception is a learned trait. The brain strategies we use to perceive the world are constantly modified by experience. With practice, we subconsciously become better at identifying familiar objects or distinguishing fine details in our environment. Current theoretical models simulate some properties of perceptual learning, but neglect the underlying cortical circuits. Future neural network models must incorporate the top-down alteration of cortical function by expectation or perceptual tasks. These newly found dynamic processes are challenging earlier views of static and feedforward processing of sensory information. PMID:15483598
Optimization with Potts Neural Networks
Söderberg, Bo
The Potts Neural Network approach to non-binary discrete optimization problems is described. It applies to problems that can be described as a set of elementary `multiple choice' options. Instead of the conventional binary (Ising) neurons, mean field Potts neurons, having several available states, are used to describe the elementary degrees of freedom of such problems. The dynamics consists of iterating the mean field equations with annealing until convergence. Due to its deterministic character, the method is quite fast. When applied to problems of Graph Partition and scheduling types, it produces very good solutions also for problems of considerable size.
System Identification, Prediction, Simulation and Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1997-01-01
a Gauss-Newton search direction is applied. 3) Amongst numerous model types, often met in control applications, only the Non-linear ARMAX (NARMAX) model, representing input/output description, is examined. A simulated example confirms that a neural network has the potential to perform excellent System...... Identification, Prediction, Simulation and Control of a dynamic, non-linear and noisy process. Further, the difficulties to control a practical non-linear laboratory process in a satisfactory way by using a traditional controller are overcomed by using a trained neural network to perform non-linear System......The intention of this paper 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...
SCYNet. Testing supersymmetric models at the LHC with neural networks
Energy Technology Data Exchange (ETDEWEB)
Bechtle, Philip; Belkner, Sebastian; Hamer, Matthias [Universitaet Bonn, Bonn (Germany); Dercks, Daniel [Universitaet Hamburg, Hamburg (Germany); Keller, Tim; Kraemer, Michael; Sarrazin, Bjoern; Schuette-Engel, Jan; Tattersall, Jamie [RWTH Aachen University, Institute for Theoretical Particle Physics and Cosmology, Aachen (Germany)
2017-10-15
SCYNet (SUSY Calculating Yield Net) is a tool for testing supersymmetric models against LHC data. It uses neural network regression for a fast evaluation of the profile likelihood ratio. Two neural network approaches have been developed: one network has been trained using the parameters of the 11-dimensional phenomenological Minimal Supersymmetric Standard Model (pMSSM-11) as an input and evaluates the corresponding profile likelihood ratio within milliseconds. It can thus be used in global pMSSM-11 fits without time penalty. In the second approach, the neural network has been trained using model-independent signature-related objects, such as energies and particle multiplicities, which were estimated from the parameters of a given new physics model. (orig.)
SCYNet: testing supersymmetric models at the LHC with neural networks
Bechtle, Philip; Belkner, Sebastian; Dercks, Daniel; Hamer, Matthias; Keller, Tim; Krämer, Michael; Sarrazin, Björn; Schütte-Engel, Jan; Tattersall, Jamie
2017-10-01
SCYNet (SUSY Calculating Yield Net) is a tool for testing supersymmetric models against LHC data. It uses neural network regression for a fast evaluation of the profile likelihood ratio. Two neural network approaches have been developed: one network has been trained using the parameters of the 11-dimensional phenomenological Minimal Supersymmetric Standard Model (pMSSM-11) as an input and evaluates the corresponding profile likelihood ratio within milliseconds. It can thus be used in global pMSSM-11 fits without time penalty. In the second approach, the neural network has been trained using model-independent signature-related objects, such as energies and particle multiplicities, which were estimated from the parameters of a given new physics model.
Suzuki, Kenji; Armato, Samuel G., III; Li, Feng; Sone, Shusuke; Doi, Kunio
2003-05-01
In this study, we investigated a pattern-classification technique which can be trained with a small number of cases with a massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose CT (LDCT). The MTANN consists of a modified multilayer artificial neural network (ANN), which is capable of operating on image data directly. The MTANN is trained by use of a large number of sub-regions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning of an input image with the MTANN. In the MTANN, the distinction between nodules and non-nodules is treated as an image-processing task, in other words, as a highly nonlinear filter that performs both nodule enhancement and non-nodule suppression. This allows us to train the MTANN not on a case basis, but on a sub-region basis. Therefore, the MTANN can be trained with a very small number of cases. Our database consisted of 101 LDCT scans acquired from 71 patients in a lung cancer screening program. The scans consisted of 2,822 sections, and contained 121 nodules including 104 nodules representing confirmed primary cancers. With our current CAD scheme, a sensitivity of 81.0% (98/121 nodules) with 0.99 false positives per section (2,804/2,822) was achieved. By use of the MTANN trained with a small number of training cases (n=10), i.e., five pairs of nodules and non-nodules, we were able to remove 55.8% of false positives without a reduction in the number of true positives, i.e., a classification sensitivity of 100%. Thus, the false-positive rate of our current CAD scheme was reduced from 0.99 to 0.44 false positive per section, while the current sensitivity (81.0%) was maintained.
Wind Resource Assessment and Forecast Planning with Neural Networks
Directory of Open Access Journals (Sweden)
Nicolus K. Rotich
2014-06-01
Full Text Available In this paper we built three types of artificial neural networks, namely: Feed forward networks, Elman networks and Cascade forward networks, for forecasting wind speeds and directions. A similar network topology was used for all the forecast horizons, regardless of the model type. All the models were then trained with real data of collected wind speeds and directions over a period of two years in the municipal of Puumala, Finland. Up to 70th percentile of the data was used for training, validation and testing, while 71–85th percentile was presented to the trained models for validation. The model outputs were then compared to the last 15% of the original data, by measuring the statistical errors between them. The feed forward networks returned the lowest errors for wind speeds. Cascade forward networks gave the lowest errors for wind directions; Elman networks returned the lowest errors when used for short term forecasting.
Research on wind field algorithm of wind lidar based on BP neural network and grey prediction
Chen, Yong; Chen, Chun-Li; Luo, Xiong; Zhang, Yan; Yang, Ze-hou; Zhou, Jie; Shi, Xiao-ding; Wang, Lei
2018-01-01
This paper uses the BP neural network and grey algorithm to forecast and study radar wind field. In order to reduce the residual error in the wind field prediction which uses BP neural network and grey algorithm, calculating the minimum value of residual error function, adopting the residuals of the gray algorithm trained by BP neural network, using the trained network model to forecast the residual sequence, using the predicted residual error sequence to modify the forecast sequence of the grey algorithm. The test data show that using the grey algorithm modified by BP neural network can effectively reduce the residual value and improve the prediction precision.
Three dimensional living neural networks
Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.
2015-08-01
We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.
A breathing circuit alarm system based on neural networks.
Orr, J A; Westenskow, D R
1994-03-01
The objectives of our study were (1) to implement intelligent respiratory alarms with a neural network; and (2) to increase alarm specificity and decrease false-alarm rates compared with current alarms. We trained a neural network to recognize 13 faults in an anesthesia breathing circuit. The system extracted 30 breath-to-breath features from the airway CO2, flow, and pressure signals. We created training data for the network by introducing 13 faults repeatedly in 5 dogs (616 total faults). We used the data to train the neural network using the backward error propagation algorithm. In animals, the trained network reported the alarms correctly for 95.0% of the faults when tested during controlled ventilation, and for 86.9% of the faults during spontaneous breathing. When tested in the operating room, the system found and correctly reported 54 of 57 faults that occurred during 43.6 hr of use. The alarm system produced a total of 74 false alarms during 43.6 hr of monitoring. Neural networks may be useful in creating intelligent anesthesia alarm systems.
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
A neural network for noise correlation classification
Paitz, Patrick; Gokhberg, Alexey; Fichtner, Andreas
2018-02-01
We present an artificial neural network (ANN) for the classification of ambient seismic noise correlations into two categories, suitable and unsuitable for noise tomography. By using only a small manually classified data subset for network training, the ANN allows us to classify large data volumes with low human effort and to encode the valuable subjective experience of data analysts that cannot be captured by a deterministic algorithm. Based on a new feature extraction procedure that exploits the wavelet-like nature of seismic time-series, we efficiently reduce the dimensionality of noise correlation data, still keeping relevant features needed for automated classification. Using global- and regional-scale data sets, we show that classification errors of 20 per cent or less can be achieved when the network training is performed with as little as 3.5 per cent and 16 per cent of the data sets, respectively. Furthermore, the ANN trained on the regional data can be applied to the global data, and vice versa, without a significant increase of the classification error. An experiment where four students manually classified the data, revealed that the classification error they would assign to each other is substantially larger than the classification error of the ANN (>35 per cent). This indicates that reproducibility would be hampered more by human subjectivity than by imperfections of the ANN.
Predicting the parameters of energy installations with laser ignition: Neural network models
Directory of Open Access Journals (Sweden)
Alexey A. Pastukhov
2015-06-01
Full Text Available This article considers the possibility of using artificial neural networks for predicting the parameters of the model energy installation with laser ignition. The main stages of creating a prognostic model based on an artificial neural network have been presented. Input data were analyzed by principal component method. The synthesized neural network was designed to predict the parameter value of the model in question. The artificial neural network was trained by a back-propagation algorithm. The efficiency of the artificial neural networks and their applicability to predicting parameter values of various rocket engine elements were demonstrated.
Li, Hong; Ding, Xue
2017-03-01
This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.
Neural network predicts sequence of TP53 gene based on DNA chip
DEFF Research Database (Denmark)
Spicker, J.S.; Wikman, F.; Lu, M.L.
2002-01-01
We have trained an artificial neural network to predict the sequence of the human TP53 tumor suppressor gene based on a p53 GeneChip. The trained neural network uses as input the fluorescence intensities of DNA hybridized to oligonucleotides on the surface of the chip and makes between zero...
Miconi, Thomas
2017-02-23
Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.
Neural adaptations to electrical stimulation strength training
Hortobagyi, Tibor; Maffiuletti, Nicola A.
2011-01-01
This review provides evidence for the hypothesis that electrostimulation strength training (EST) increases the force of a maximal voluntary contraction (MVC) through neural adaptations in healthy skeletal muscle. Although electrical stimulation and voluntary effort activate muscle differently, there
Predicting local field potentials with recurrent neural networks.
Kim, Louis; Harer, Jacob; Rangamani, Akshay; Moran, James; Parks, Philip D; Widge, Alik; Eskandar, Emad; Dougherty, Darin; Chin, Sang Peter
2016-08-01
We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.
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...
Hindcasting of storm waves using neural networks
Digital Repository Service at National Institute of Oceanography (India)
Rao, S.; Mandal, S.
of any exogenous input requirement makes the network attractive. A neural network is an information processing system modeled on the structure of the human brain. Its merit is the ability to deal with fuzzy information whose interrelation is ambiguous...
Artificial Neural Networks for Nonlinear Dynamic Response Simulation in Mechanical Systems
DEFF Research Database (Denmark)
Christiansen, Niels Hørbye; Høgsberg, Jan Becker; Winther, Ole
2011-01-01
It is shown how artificial neural networks can be trained to predict dynamic response of a simple nonlinear structure. Data generated using a nonlinear finite element model of a simplified wind turbine is used to train a one layer artificial neural network. When trained properly the network is ab...... to perform accurate response prediction much faster than the corresponding finite element model. Initial result indicate a reduction in cpu time by two orders of magnitude.......It is shown how artificial neural networks can be trained to predict dynamic response of a simple nonlinear structure. Data generated using a nonlinear finite element model of a simplified wind turbine is used to train a one layer artificial neural network. When trained properly the network is able...
Directory of Open Access Journals (Sweden)
Shuihua Wang
2015-08-01
Full Text Available Fruit classification is quite difficult because of the various categories and similar shapes and features of fruit. In this work, we proposed two novel machine-learning based classification methods. The developed system consists of wavelet entropy (WE, principal component analysis (PCA, feedforward neural network (FNN trained by fitness-scaled chaotic artificial bee colony (FSCABC and biogeography-based optimization (BBO, respectively. The K-fold stratified cross validation (SCV was utilized for statistical analysis. The classification performance for 1653 fruit images from 18 categories showed that the proposed “WE + PCA + FSCABC-FNN” and “WE + PCA + BBO-FNN” methods achieve the same accuracy of 89.5%, higher than state-of-the-art approaches: “(CH + MP + US + PCA + GA-FNN ” of 84.8%, “(CH + MP + US + PCA + PSO-FNN” of 87.9%, “(CH + MP + US + PCA + ABC-FNN” of 85.4%, “(CH + MP + US + PCA + kSVM” of 88.2%, and “(CH + MP + US + PCA + FSCABC-FNN” of 89.1%. Besides, our methods used only 12 features, less than the number of features used by other methods. Therefore, the proposed methods are effective for fruit classification.
Artificial Neural Network applied to lightning flashes
Gin, R. B.; Guedes, D.; Bianchi, R.
2013-05-01
The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a
An artifical neural network for detection of simulated dental caries
Energy Technology Data Exchange (ETDEWEB)
Kositbowornchai, S. [Khon Kaen Univ. (Thailand). Dept. of Oral Diagnosis; Siriteptawee, S.; Plermkamon, S.; Bureerat, S. [Khon Kaen Univ. (Thailand). Dept. of Mechanical Engineering; Chetchotsak, D. [Khon Kaen Univ. (Thailand). Dept. of Industrial Engineering
2006-08-15
Objects: A neural network was developed to diagnose artificial dental caries using images from a charged-coupled device (CCD)camera and intra-oral digital radiography. The diagnostic performance of this neural network was evaluated against a gold standard. Materials and methods: The neural network design was the Learning Vector Quantization (LVQ) used to classify a tooth surface as sound or as having dental caries. The depth of the dental caries was indicated on a graphic user interface (GUI) screen developed by Matlab programming. Forty-nine images of both sound and simulated dental caries, derived from a CCD camera and by digital radiography, were used to 'train' an artificial neural network. After the 'training' process, a separate test-set comprising 322 unseen images was evaluated. Tooth sections and microscopic examinations were used to confirm the actual dental caries status.The performance of neural network was evaluated using diagnostic test. Results: The sensitivity (95%CI)/specificity (95%CI) of dental caries detection by the CCD camera and digital radiography were 0.77(0.68-0.85)/0.85(0.75-0.92) and 0.81(0.72-0.88)/0.93(0.84-0.97), respectively. The accuracy of caries depth-detection by the CCD camera and digital radiography was 58 and 40%, respectively. Conclusions: The model neural network used in this study could be a prototype for caries detection but should be improved for classifying caries depth. Our study suggests an artificial neural network can be trained to make the correct interpretations of dental caries. (orig.)
Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
CERN. Geneva
2017-01-01
We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved discovery significance relative to existing taggers. The network is trained using an adversarial strategy, resulting in a tagger that learns to balance classification accuracy with decorrelation. As a benchmark scenario, we consider the case where large-radius jets originating from a boosted Z' decay are discriminated from a background of nonresonant quark and gluon jets. We show that in the presence of systematic uncertainties on the background rate, our adversarially-trained, decorrelated tagger considerably outperforms a conventionally trained neural network, despite having a slightly worse signal-background separation power. We generalize the adversarial training technique to include a paramet...
Application of Artificial Neural Networks in the Heart Electrical Axis Position Conclusion Modeling
Bakanovskaya, L. N.
2016-08-01
The article touches upon building of a heart electrical axis position conclusion model using an artificial neural network. The input signals of the neural network are the values of deflections Q, R and S; and the output signal is the value of the heart electrical axis position. Training of the network is carried out by the error propagation method. The test results allow concluding that the created neural network makes a conclusion with a high degree of accuracy.
Deep Gate Recurrent Neural Network
2016-11-22
distribution, e.g. a particular book. In this experiment, we use a collection of writings by Nietzsche to train our network. In total, this corpus contains...sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics : Human Language Technologies, pages 142–150...Portland, Oregon, USA, June 2011. Association for Com- putational Linguistics . URL http://www.aclweb.org/anthology/P11-1015. Maja J Matari, Complex
Constitutive Modelling of INCONEL 718 using Artificial Neural Network
Abiriand Bhekisipho Twala, Olufunminiyi
2017-08-01
Artificial neural network is used to model INCONEL 718 in this paper. The model accounts for precipitate hardening in the alloy. The input variables for the neural network model are strain, strain rate, temperature and microstructure state. The output variable is the flow stress. The early stopping technique is combined with Bayesian regularization process in training the network. Sample and non-sample measurement data were taken from the literature. The model predictions of flow stress of the alloy are in good agreement with experimental measurements.
Suzuki, Kenji
2009-09-01
Computer-aided diagnosis (CAD) has been an active area of study in medical image analysis. A filter for the enhancement of lesions plays an important role for improving the sensitivity and specificity in CAD schemes. The filter enhances objects similar to a model employed in the filter; e.g. a blob-enhancement filter based on the Hessian matrix enhances sphere-like objects. Actual lesions, however, often differ from a simple model; e.g. a lung nodule is generally modeled as a solid sphere, but there are nodules of various shapes and with internal inhomogeneities such as a nodule with spiculations and ground-glass opacity. Thus, conventional filters often fail to enhance actual lesions. Our purpose in this study was to develop a supervised filter for the enhancement of actual lesions (as opposed to a lesion model) by use of a massive-training artificial neural network (MTANN) in a CAD scheme for detection of lung nodules in CT. The MTANN filter was trained with actual nodules in CT images to enhance actual patterns of nodules. By use of the MTANN filter, the sensitivity and specificity of our CAD scheme were improved substantially. With a database of 69 lung cancers, nodule candidate detection by the MTANN filter achieved a 97% sensitivity with 6.7 false positives (FPs) per section, whereas nodule candidate detection by a difference-image technique achieved a 96% sensitivity with 19.3 FPs per section. Classification-MTANNs were applied for further reduction of the FPs. The classification-MTANNs removed 60% of the FPs with a loss of one true positive; thus, it achieved a 96% sensitivity with 2.7 FPs per section. Overall, with our CAD scheme based on the MTANN filter and classification-MTANNs, an 84% sensitivity with 0.5 FPs per section was achieved. First presented at the Seventh International Conference on Machine Learning and Applications, San Diego, CA, USA, 11-13 December 2008.
Sauer, J.; Travis, B. J.; Munoz-Esparza, D.; Dubey, M. K.
2015-12-01
Fugitive methane (CH4) leaks from oil and gas production fields are a potential significant source of atmospheric methane. US DOE's ARPA-E MONITOR program is supporting research to locate and quantify fugitive methane leaks at natural gas facilities in order to achieve a 90% reduction in CH4 emissions. LANL, Aeris and Rice University are developing an LDS (leak detection system) that employs a compact laser absorption methane sensor and sonic anemometer coupled to an artificial neural network (ANN)-based source attribution algorithm. LANL's large-eddy simulation model, HIGRAD, provides high-fidelity simulated wind fields and turbulent CH4 plume dispersion data for various scenarios used in training the ANN. Numerous inverse solution methodologies have been applied over the last decade to assessment of greenhouse gas emissions. ANN learning is well suited to problems in which the training and observed data are noisy, or correspond to complex sensor data as is typical of meteorological and sensor data over a site. ANNs have been shown to achieve higher accuracy with more efficiency than other inverse modeling approaches in studies at larger scales, in urban environments, over short time scales, and even at small spatial scales for efficient source localization of indoor airborne contaminants. Our ANN is intended to characterize fugitive leaks rapidly, given site-specific, real-time, wind and CH4 concentration time-series data at multiple sensor locations, leading to a minimum time-to-detection and providing a first order improvement with respect to overall minimization of methane loss. Initial studies with the ANN on a variety of source location, sensor location, and meteorological condition scenarios are presented and discussed.
Radiation Behavior of Analog Neural Network Chip
Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.
1996-01-01
A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.
Self-organization of neural networks
Energy Technology Data Exchange (ETDEWEB)
Clark, J.W.; Winston, J.V.; Rafelski, J.
1984-05-14
The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (brainwashing) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conducive to the simulation of memory and learning phenomena. 18 references, 2 figures.
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...
Genetic Algorithm Optimized Neural Networks Ensemble as ...
African Journals Online (AJOL)
Improvements in neural network calibration models by a novel approach using neural network ensemble (NNE) for the simultaneous spectrophotometric multicomponent analysis are suggested, with a study on the estimation of the components of an antihypertensive combination, namely, atenolol and losartan potassium.
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 Network to Solve Concave Games
Zixin Liu; Nengfa Wang
2014-01-01
The issue on neural network method to solve concave games is concerned. Combined with variational inequality, Ky Fan inequality, and projection equation, concave games are transformed into a neural network model. On the basis of the Lyapunov stable theory, some stability results are also given. Finally, two classic games’ simulation results are given to illustrate the theoretical results.
Recognizing changing seasonal patterns using neural networks
Ph.H.B.F. Franses (Philip Hans); G. Draisma (Gerrit)
1997-01-01
textabstractIn this paper we propose a graphical method based on an artificial neural network model to investigate how and when seasonal patterns in macroeconomic time series change over time. Neural networks are useful since the hidden layer units may become activated only in certain seasons or
Initialization of multilayer forecasting artifical neural networks
Bochkarev, Vladimir V.; Maslennikova, Yulia S.
2014-01-01
In this paper, a new method was developed for initialising artificial neural networks predicting dynamics of time series. Initial weighting coefficients were determined for neurons analogously to the case of a linear prediction filter. Moreover, to improve the accuracy of the initialization method for a multilayer neural network, some variants of decomposition of the transformation matrix corresponding to the linear prediction filter were suggested. The efficiency of the proposed neural netwo...
Hand-Eye Calibration and Inverse Kinematics of Robot Arm using Neural Network
DEFF Research Database (Denmark)
Wu, Haiyan; Tizzano, Walter; Andersen, Thomas Timm
2013-01-01
tasks. This paper describes the theory and implementation of neural networks for hand-eye calibration and inverse kinematics of a six degrees of freedom robot arm equipped with a stereo vision system. The feedforward neural network and the network training with error propagation algorithm are applied...
Neural networks art: solving problems with multiple solutions and new teaching algorithm.
Dmitrienko, V D; Zakovorotnyi, A Yu; Leonov, S Yu; Khavina, I P
2014-01-01
A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input.
Stable architectures for deep neural networks
Haber, Eldad; Ruthotto, Lars
2018-01-01
Deep neural networks have become invaluable tools for supervised machine learning, e.g. classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in data, deep architectures are known to be challenging to design and train such that they generalize well to new data. Critical issues with deep architectures are numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients. In this paper, we propose new forward propagation techniques inspired by systems of ordinary differential equations (ODE) that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks. The backbone of our approach is our interpretation of deep learning as a parameter estimation problem of nonlinear dynamical systems. Given this formulation, we analyze stability and well-posedness of deep learning and use this new understanding to develop new network architectures. We relate the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and present several strategies for stabilizing deep learning for very deep networks. While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.
HIV lipodystrophy case definition using artificial neural network modelling
DEFF Research Database (Denmark)
Ioannidis, John P A; Trikalinos, Thomas A; Law, Matthew
2003-01-01
OBJECTIVE: A case definition of HIV lipodystrophy has recently been developed from a combination of clinical, metabolic and imaging/body composition variables using logistic regression methods. We aimed to evaluate whether artificial neural networks could improve the diagnostic accuracy. METHODS......: The database of the case-control Lipodystrophy Case Definition Study was split into 504 subjects (265 with and 239 without lipodystrophy) used for training and 284 independent subjects (152 with and 132 without lipodystrophy) used for validation. Back-propagation neural networks with one or two middle layers...... were trained and validated. Results were compared against logistic regression models using the same information. RESULTS: Neural networks using clinical variables only (41 items) achieved consistently superior performance than logistic regression in terms of specificity, overall accuracy and area under...
DEFF Research Database (Denmark)
May, Tobias
2018-01-01
This study presents an algorithm for binaural speech dereverberation based on the supervised learning of short-term binaural cues. The proposed system combined a delay-and-sum beamformer (DSB) with a neural network-based post-filter that attenuated reverberant components in individual time...
A Neural Network Model for Prediction of Sound Quality
DEFF Research Database (Denmark)
Nielsen,, Lars Bramsløw
An artificial neural network structure has been specified, implemented and optimized for the purpose of predicting the perceived sound quality for normal-hearing and hearing-impaired subjects. The network was implemented by means of commercially available software and optimized to predict results...... error on the test set. The overall concept proved functional, but further testing with data obtained from a new rating experiment is necessary to better assess the utility of this measure. The weights in the trained neural networks were analyzed to qualitatively interpret the relation between...... obtained in subjective sound quality rating experiments based on input data from an auditory model. Various types of input data and data representations from the auditory model were used as input data for the chosen network structure, which was a three-layer perceptron. This network was trained by means...
Synthesis of recurrent neural networks for dynamical system simulation.
Trischler, Adam P; D'Eleuterio, Gabriele M T
2016-08-01
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time. Copyright © 2016 Elsevier Ltd. All rights reserved.
Optimization of multilayer neural network parameters for speaker recognition
Tovarek, Jaromir; Partila, Pavol; Rozhon, Jan; Voznak, Miroslav; Skapa, Jan; Uhrin, Dominik; Chmelikova, Zdenka
2016-05-01
This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.
Neural Based Orthogonal Data Fitting The EXIN Neural Networks
Cirrincione, Giansalvo
2008-01-01
Written by three leaders in the field of neural based algorithms, Neural Based Orthogonal Data Fitting proposes several neural networks, all endowed with a complete theory which not only explains their behavior, but also compares them with the existing neural and traditional algorithms. The algorithms are studied from different points of view, including: as a differential geometry problem, as a dynamic problem, as a stochastic problem, and as a numerical problem. All algorithms have also been analyzed on real time problems (large dimensional data matrices) and have shown accurate solutions. Wh
Reliability Modeling of Microelectromechanical Systems Using Neural Networks
Perera. J. Sebastian
2000-01-01
Microelectromechanical systems (MEMS) are a broad and rapidly expanding field that is currently receiving a great deal of attention because of the potential to significantly improve the ability to sense, analyze, and control a variety of processes, such as heating and ventilation systems, automobiles, medicine, aeronautical flight, military surveillance, weather forecasting, and space exploration. MEMS are very small and are a blend of electrical and mechanical components, with electrical and mechanical systems on one chip. This research establishes reliability estimation and prediction for MEMS devices at the conceptual design phase using neural networks. At the conceptual design phase, before devices are built and tested, traditional methods of quantifying reliability are inadequate because the device is not in existence and cannot be tested to establish the reliability distributions. A novel approach using neural networks is created to predict the overall reliability of a MEMS device based on its components and each component's attributes. The methodology begins with collecting attribute data (fabrication process, physical specifications, operating environment, property characteristics, packaging, etc.) and reliability data for many types of microengines. The data are partitioned into training data (the majority) and validation data (the remainder). A neural network is applied to the training data (both attribute and reliability); the attributes become the system inputs and reliability data (cycles to failure), the system output. After the neural network is trained with sufficient data. the validation data are used to verify the neural networks provided accurate reliability estimates. Now, the reliability of a new proposed MEMS device can be estimated by using the appropriate trained neural networks developed in this work.
Clustering: a neural network approach.
Du, K-L
2010-01-01
Clustering is a fundamental data analysis method. It is widely used for pattern recognition, feature extraction, vector quantization (VQ), image segmentation, function approximation, and data mining. As an unsupervised classification technique, clustering identifies some inherent structures present in a set of objects based on a similarity measure. Clustering methods can be based on statistical model identification (McLachlan & Basford, 1988) or competitive learning. In this paper, we give a comprehensive overview of competitive learning based clustering methods. Importance is attached to a number of competitive learning based clustering neural networks such as the self-organizing map (SOM), the learning vector quantization (LVQ), the neural gas, and the ART model, and clustering algorithms such as the C-means, mountain/subtractive clustering, and fuzzy C-means (FCM) algorithms. Associated topics such as the under-utilization problem, fuzzy clustering, robust clustering, clustering based on non-Euclidean distance measures, supervised clustering, hierarchical clustering as well as cluster validity are also described. Two examples are given to demonstrate the use of the clustering methods.
Complex-valued Neural Networks
Hirose, Akira
This paper reviews the features and applications of complex-valued neural networks (CVNNs). First we list the present application fields, and describe the advantages of the CVNNs in two application examples, namely, an adaptive plastic-landmine visualization system and an optical frequency-domain-multiplexed learning logic circuit. Then we briefly discuss the features of complex number itself to find that the phase rotation is the most significant concept, which is very useful in processing the information related to wave phenomena such as lightwave and electromagnetic wave. The CVNNs will also be an indispensable framework of the future microelectronic information-processing hardware where the quantum electron wave plays the principal role.
Tampa Electric Neural Network Sootblowing
Energy Technology Data Exchange (ETDEWEB)
Mark A. Rhode
2003-12-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat
Tampa Electric Neural Network Sootblowing
Energy Technology Data Exchange (ETDEWEB)
Mark A. Rhode
2004-09-30
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate
Tampa Electric Neural Network Sootblowing
Energy Technology Data Exchange (ETDEWEB)
Mark A. Rhode
2004-03-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing co-funding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate
Training brain networks and states.
Tang, Yi-Yuan; Posner, Michael I
2014-07-01
Brain training refers to practices that alter the brain in a way that improves cognition, and performance in domains beyond those involved in the training. We argue that brain training includes network training through repetitive practice that exercises specific brain networks and state training, which changes the brain state in a way that influences many networks. This opinion article considers two widely used methods - working memory training (WMT) and meditation training (MT) - to demonstrate the similarities and differences between network and state training. These two forms of training involve different areas of the brain and different forms of generalization. We propose a distinction between network and state training methods to improve understanding of the most effective brain training. Copyright © 2014 Elsevier Ltd. All rights reserved.
Steam turbine stress control using NARX neural network
Dominiczak, Krzysztof; Rzadkowski, Romuald; Radulski, Wojciech
2015-11-01
Considered here is concept of steam turbine stress control, which is based on Nonlinear AutoRegressive neural networks with eXogenous inputs. Using NARX neural networks,whichwere trained based on experimentally validated FE model allows to control stresses in protected thickwalled steam turbine element with FE model quality. Additionally NARX neural network, which were trained base on FE model, includes: nonlinearity of steam expansion in turbine steam path during transients, nonlinearity of heat exchange inside the turbine during transients and nonlinearity of material properties during transients. In this article NARX neural networks stress controls is shown as an example of HP rotor of 18K390 turbine. HP part thermodynamic model as well as heat exchange model in vicinity of HP rotor,whichwere used in FE model of the HP rotor and the HP rotor FE model itself were validated based on experimental data for real turbine transient events. In such a way it is ensured that NARX neural network behave as real HP rotor during steam turbine transient events.
Kontrol Kecepatan Motor Induksi menggunakan Algoritma Backpropagation Neural Network
Directory of Open Access Journals (Sweden)
MUHAMMAD RUSWANDI DJALAL
2017-07-01
Full Text Available ABSTRAKBanyak strategi kontrol berbasis kecerdasan buatan telah diusulkan dalam penelitian seperti Fuzzy Logic dan Artificial Neural Network (ANN. Tujuan dari penelitian ini adalah untuk mendesain sebuah kontrol agar kecepatan motor induksi dapat diatur sesuai kebutuhan serta membandingkan kinerja motor induksi tanpa kontrol dan dengan kontrol. Dalam penelitian ini diusulkan sebuah metode artificial neural network untuk mengontrol kecepatan motor induksi tiga fasa. Kecepatan referensi motor diatur pada kecepatan 140 rad/s, 150 rad/s, dan 130 rad/s. Perubahan kecepatan diatur pada setiap interval 0.3 detik dan waktu simulasi maksimum adalah 0,9 detik. Kasus 1 tanpa kontrol, menunjukkan respon torka dan kecepatan dari motor induksi tiga fasa tanpa kontrol. Meskipun kecepatan motor induksi tiga fasa diatur berubah pada setiap 0,3 detik tidak akan mempengaruhi torka. Selain itu, motor induksi tiga fasa tanpa kontrol memiliki kinerja yang buruk dikarenakan kecepatan motor induksi tidak dapat diatur sesuai dengan kebutuhan. Kasus 2 dengan control backpropagation neural network, meskipun kecepatan motor induksi tiga fasa berubah pada setiap 0.3 detik tidak akan mempengaruhi torsi. Selain itu, kontrol backpropagation neural network memiliki kinerja yang baik dikarenakan kecepatan motor induksi dapat diatur sesuai dengan kebutuhan.Kata kunci: Backpropagation Neural Network (BPNN, NN Training, NN Testing, Motor.ABSTRACTMany artificial intelligence-based control strategies have been proposed in research such as Fuzzy Logic and Artificial Neural Network (ANN. The purpose of this research was design a control for the induction motor speed that could be adjusted as needed and compare the performance of induction motor without control and with control. In this research, it was proposed an artificial neural network method to control the speed of three-phase induction motors. The reference speed of motor was set at the rate of 140 rad / s, 150 rad / s, and 130
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.
Data Driven Broiler Weight Forecasting using Dynamic Neural Network Models
DEFF Research Database (Denmark)
Johansen, Simon Vestergaard; Bendtsen, Jan Dimon; Riisgaard-Jensen, Martin
2017-01-01
In this article, the dynamic influence of environmental broiler house conditions and broiler growth is investigated. Dynamic neural network forecasting models have been trained on farm-scale broiler batch production data from 12 batches from the same house. The model forecasts future broiler weight...
Wind Power Plant Prediction by Using Neural Networks: Preprint
Energy Technology Data Exchange (ETDEWEB)
Liu, Z.; Gao, W.; Wan, Y. H.; Muljadi, E.
2012-08-01
This paper introduces a method of short-term wind power prediction for a wind power plant by training neural networks based on historical data of wind speed and wind direction. The model proposed is shown to achieve a high accuracy with respect to the measured data.
Neural networks applied to the classification of remotely sensed data
Mulder, Nanno; Spreeuwers, Lieuwe Jan
1991-01-01
A neural network with topology 2-8-8 is evaluated against the standard of supervised non-parametric maximum likelihood classification. The purpose of the evaluation is to compare the performance in terms of training speed and quality of classification. Classification is done on multispectral data
Numerical simulation with finite element and artificial neural network ...
Indian Academy of Sciences (India)
Further, this database after the neural network training; is used to analyse measured material properties of different test pieces. The ANN predictions are reconﬁrmed with contact type ﬁnite element analysis for an arbitrary selected test sample. The methodology evolved in this work can be extended to predict material ...
NNSYSID - toolbox for system identification with neural networks
DEFF Research Database (Denmark)
Norgaard, M.; Ravn, Ole; Poulsen, Niels Kjølstad
2002-01-01
The NNSYSID toolset for System Identification has been developed as an add on to MATLAB(R). The NNSYSID toolbox has been designed to assist identification of nonlinear dynamic systems. It contains a number of nonlinear model structures based on neural networks, effective training algorithms...
Using Artificial Neural Networks for ECG Signals Denoising
Directory of Open Access Journals (Sweden)
Zoltán Germán-Salló
2010-12-01
Full Text Available The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1th sample from n previous samples To train and adjust the network weights, the backpropagation (BP algorithm was used. In this paper, prediction of ECG signals (as time series using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.
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. Copyright © 2016 Elsevier B.V. All rights reserved.
Prediction of proteasome cleavage motifs by neural networks
DEFF Research Database (Denmark)
Kesimir, C.; Nussbaum, A.K.; Schild, H.
2002-01-01
physiological conditions. Our algorithm has been trained not only on in vitro data, but also on MHC Class I ligand data, which reflect a combination of immunoproteasome and constitutive proteasome specificity. This feature, together with the use of neural networks, a non-linear classification technique, make...... the prediction of MHC Class I ligand boundaries more accurate: 65% of the cleavage sites and 85% of the non-cleavage sites are correctly determined. Moreover, we show that the neural networks trained on the constitutive proteasome data learns a specificity that differs from that of the networks trained on MHC...... Class I molecules. Here we demonstrate that such an approach produces an accurate prediction of the CTL the epitopes in HIV Nef. The method is available at www.cbs.dtu.dk/services/NetChop/....
Piecewise convexity of artificial neural networks.
Rister, Blaine; Rubin, Daniel L
2017-10-01
Although artificial neural networks have shown great promise in applications including computer vision and speech recognition, there remains considerable practical and theoretical difficulty in optimizing their parameters. The seemingly unreasonable success of gradient descent methods in minimizing these non-convex functions remains poorly understood. In this work we offer some theoretical guarantees for networks with piecewise affine activation functions, which have in recent years become the norm. We prove three main results. First, that the network is piecewise convex as a function of the input data. Second, that the network, considered as a function of the parameters in a single layer, all others held constant, is again piecewise convex. Third, that the network as a function of all its parameters is piecewise multi-convex, a generalization of biconvexity. From here we characterize the local minima and stationary points of the training objective, showing that they minimize the objective on certain subsets of the parameter space. We then analyze the performance of two optimization algorithms on multi-convex problems: gradient descent, and a method which repeatedly solves a number of convex sub-problems. We prove necessary convergence conditions for the first algorithm and both necessary and sufficient conditions for the second, after introducing regularization to the objective. Finally, we remark on the remaining difficulty of the global optimization problem. Under the squared error objective, we show that by varying the training data, a single rectifier neuron admits local minima arbitrarily far apart, both in objective value and parameter space. Copyright © 2017 Elsevier Ltd. All rights reserved.
Shimray, Benjamin A; Singh, Kh Manglem; Khelchandra, Thongam; Mehta, R K
2017-01-01
Every energy system which we consider is an entity by itself, defined by parameters which are interrelated according to some physical laws. In recent year tremendous importance is given in research on site selection in an imprecise environment. In this context, decision making for the suitable location of power plant installation site is an issue of relevance. Environmental impact assessment is often used as a legislative requirement in site selection for decades. The purpose of this current work is to develop a model for decision makers to rank or classify various power plant projects according to multiple criteria attributes such as air quality, water quality, cost of energy delivery, ecological impact, natural hazard, and project duration. The case study in the paper relates to the application of multilayer perceptron trained by genetic algorithm for ranking various power plant locations in India.
Directory of Open Access Journals (Sweden)
Benjamin A. Shimray
2017-01-01
Full Text Available Every energy system which we consider is an entity by itself, defined by parameters which are interrelated according to some physical laws. In recent year tremendous importance is given in research on site selection in an imprecise environment. In this context, decision making for the suitable location of power plant installation site is an issue of relevance. Environmental impact assessment is often used as a legislative requirement in site selection for decades. The purpose of this current work is to develop a model for decision makers to rank or classify various power plant projects according to multiple criteria attributes such as air quality, water quality, cost of energy delivery, ecological impact, natural hazard, and project duration. The case study in the paper relates to the application of multilayer perceptron trained by genetic algorithm for ranking various power plant locations in India.
Neural Networks For Electrohydrodynamic Effect Modelling
Directory of Open Access Journals (Sweden)
Wiesław Wajs
2004-01-01
Full Text Available This paper presents currently achieved results concerning methods of electrohydrodynamiceffect used in geophysics simulated with feedforward networks trained with backpropagation algorithm, radial basis function networks and generalized regression networks.
Neural network structure for navigation using potential fields
Plumer, Edward S.
1992-01-01
A hybrid-network method for obstacle avoidance in the truck-backing system of D. Nguyen and B. Widrow (1989) is presented. A neural network technique for vehicle navigation and control in the presence of obstacles has been developed. A potential function which peaks at the surface of obstacles and has its minimum at the proper vehicle destination is computed using a network structure. The field is guaranteed not to have spurious local minima and does not have the property of flattening-out far from the goal. A feedforward neural network is used to control the steering of the vehicle using local field information. The network is trained in an obstacle-free space to follow the negative gradient of the field, after which the network is able to control and navigate the truck to its target destination in a space of obstacles which may be stationary or movable.
Adaptive model predictive process control using neural networks
Buescher, K.L.; Baum, C.C.; Jones, R.D.
1997-08-19
A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data. 46 figs.
Sign Language Recognition using Neural Networks
Directory of Open Access Journals (Sweden)
Sabaheta Djogic
2014-11-01
Full Text Available – Sign language plays a great role as communication media for people with hearing difficulties.In developed countries, systems are made for overcoming a problem in communication with deaf people. This encouraged us to develop a system for the Bosnian sign language since there is a need for such system. The work is done with the use of digital image processing methods providing a system that teaches a multilayer neural network using a back propagation algorithm. Images are processed by feature extraction methods, and by masking method the data set has been created. Training is done using cross validation method for better performance thus; an accuracy of 84% is achieved.
METHODS OF TEXT INFORMATION CLASSIFICATION ON THE BASIS OF ARTIFICIAL NEURAL AND SEMANTIC NETWORKS
L. V. Serebryanaya; V. V. Potaraev
2016-01-01
The article covers the use of perseptron, Hopfild artificial neural network and semantic network for classification of text information. Network training algorithms are studied. An algorithm of inverse mistake spreading for perceptron network and convergence algorithm for Hopfild network are implemented. On the basis of the offered models and algorithms automatic text classification software is developed and its operation results are evaluated.
Training for Micrographia Alters Neural Connectivity in Parkinson's Disease
Directory of Open Access Journals (Sweden)
Evelien Nackaerts
2018-01-01
Full Text Available Despite recent advances in clarifying the neural networks underlying rehabilitation in Parkinson's disease (PD, the impact of prolonged motor learning interventions on brain connectivity in people with PD is currently unknown. Therefore, the objective of this study was to compare cortical network changes after 6 weeks of visually cued handwriting training (= experimental with a placebo intervention to address micrographia, a common problem in PD. Twenty seven early Parkinson's patients on dopaminergic medication performed a pre-writing task in both the presence and absence of visual cues during behavioral tests and during fMRI. Subsequently, patients were randomized to the experimental (N = 13 or placebo intervention (N = 14 both lasting 6 weeks, after which they underwent the same testing procedure. We used dynamic causal modeling to compare the neural network dynamics in both groups before and after training. Most importantly, intensive writing training propagated connectivity via the left hemispheric visuomotor stream to an increased coupling with the supplementary motor area, not witnessed in the placebo group. Training enhanced communication in the left visuomotor integration system in line with the learned visually steered training. Notably, this pattern was apparent irrespective of the presence of cues, suggesting transfer from cued to uncued handwriting. We conclude that in early PD intensive motor skill learning, which led to clinical improvement, alters cortical network functioning. We showed for the first time in a placebo-controlled design that it remains possible to enhance the drive to the supplementary motor area through motor learning.
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«.
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....
Vectorized algorithms for spiking neural network simulation.
Brette, Romain; Goodman, Dan F M
2011-06-01
High-level languages (Matlab, Python) are popular in neuroscience because they are flexible and accelerate development. However, for simulating spiking neural networks, the cost of interpretation is a bottleneck. We describe a set of algorithms to simulate large spiking neural networks efficiently with high-level languages using vector-based operations. These algorithms constitute the core of Brian, a spiking neural network simulator written in the Python language. Vectorized simulation makes it possible to combine the flexibility of high-level languages with the computational efficiency usually associated with compiled languages.
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.
Lung cancer classification using neural networks for CT images.
Kuruvilla, Jinsa; Gunavathi, K
2014-01-01
Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer aided classification method in computed tomography (CT) images of lungs developed using artificial neural network. The entire lung is segmented from the CT images and the parameters are calculated from the segmented image. The statistical parameters like mean, standard deviation, skewness, kurtosis, fifth central moment and sixth central moment are used for classification. The classification process is done by feed forward and feed forward back propagation neural networks. Compared to feed forward networks the feed forward back propagation network gives better classification. The parameter skewness gives the maximum classification accuracy. Among the already available thirteen training functions of back propagation neural network, the Traingdx function gives the maximum classification accuracy of 91.1%. Two new training functions are proposed in this paper. The results show that the proposed training function 1 gives an accuracy of 93.3%, specificity of 100% and sensitivity of 91.4% and a mean square error of 0.998. The proposed training function 2 gives a classification accuracy of 93.3% and minimum mean square error of 0.0942. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.
Inline hyperspectral thickness determination of thin films using neural networks
Tremmel, Anton J.; Weiss, Roman; Schardt, Michael; Koch, Alexander W.
2017-04-01
Combining reflectometry and hyperspectral imaging allows mapping of thin film thickness. Therefore, layer thickness is calculated by comparing a dataset of simulated spectra with the measured data. Utilizing the maximum frame rate of the hyperspectral imager, the pixel wise spectra comparing procedure cannot be performed using a standard computer due to the processing load. In this work, a method using neural networks for calculating layer thickness is presented. By the use of the nonlinear equation as result of a trained neural network, thickness data can be determined with a measurement rate matching the maximum frame rate of the hyperspectral imager.
Hand gesture recognition based on convolutional neural networks
Hu, Yu-lu; Wang, Lian-ming
2017-11-01
Hand gesture has been considered a natural, intuitive and less intrusive way for Human-Computer Interaction (HCI). Although many algorithms for hand gesture recognition have been proposed in literature, robust algorithms have been pursued. A recognize algorithm based on the convolutional neural networks is proposed to recognize ten kinds of hand gestures, which include rotation and turnover samples acquired from different persons. When 6000 hand gesture images were used as training samples, and 1100 as testing samples, a 98% recognition rate was achieved with the convolutional neural networks, which is higher than that with some other frequently-used recognition algorithms.
Modelling of word usage frequency dynamics using artificial neural network
Maslennikova, Yu S.; Bochkarev, V. V.; Voloskov, D. S.
2014-03-01
In this paper the method for modelling of word usage frequency time series is proposed. An artificial feedforward neural network was used to predict word usage frequencies. The neural network was trained using the maximum likelihood criterion. The Google Books Ngram corpus was used for the analysis. This database provides a large amount of data on frequency of specific word forms for 7 languages. Statistical modelling of word usage frequency time series allows finding optimal fitting and filtering algorithm for subsequent lexicographic analysis and verification of frequency trend models.
Low-dose CT denoising with convolutional neural network
Chen, Hu; Zhang, Weihua; Liao, Peixi; Li, Ke; Zhou, Jiliu; Wang, Ge
2016-01-01
To reduce the potential radiation risk, low-dose CT has attracted much attention. However, simply lowering the radiation dose will lead to significant deterioration of the image quality. In this paper, we propose a noise reduction method for low-dose CT via deep neural network without accessing original projection data. A deep convolutional neural network is trained to transform low-dose CT images towards normal-dose CT images, patch by patch. Visual and quantitative evaluation demonstrates a competing performance of the proposed method.
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
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...
Galeazzi, Juan M.; Navajas, Joaquin; Mender, Bedeho M. W.; Quian Quiroga, Rodrigo; Minini, Loredana; Stringer, Simon M.
2016-01-01
ABSTRACT Neurons have been found in the primate brain that respond to objects in specific locations in hand-centered coordinates. A key theoretical challenge is to explain how such hand-centered neuronal responses may develop through visual experience. In this paper we show how hand-centered visual receptive fields can develop using an artificial neural network model, VisNet, of the primate visual system when driven by gaze changes recorded from human test subjects as they completed a jigsaw....
Artificial Neural Networks to Detect Risk of Type 2 Diabetes | Baha ...
African Journals Online (AJOL)
A multilayer feedforward architecture with backpropagation algorithm was designed using Neural Network Toolbox of Matlab. The network was trained using batch mode backpropagation with gradient descent and momentum. Best performed network identified during the training was 2 hidden layers of 6 and 3 neurons, ...
Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis
Chernoded, Andrey; Dudko, Lev; Myagkov, Igor; Volkov, Petr
2017-10-01
Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.
Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis
Directory of Open Access Journals (Sweden)
Chernoded Andrey
2017-01-01
Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.
Neural networks to formulate special fats
Directory of Open Access Journals (Sweden)
Garcia, R. K.
2012-09-01
Full Text Available Neural networks are a branch of artificial intelligence based on the structure and development of biological systems, having as its main characteristic the ability to learn and generalize knowledge. They are used for solving complex problems for which traditional computing systems have a low efficiency. To date, applications have been proposed for different sectors and activities. In the area of fats and oils, the use of neural networks has focused mainly on two issues: the detection of adulteration and the development of fatty products. The formulation of fats for specific uses is the classic case of a complex problem where an expert or group of experts defines the proportions of each base, which, when mixed, provide the specifications for the desired product. Some conventional computer systems are currently available to assist the experts; however, these systems have some shortcomings. This article describes in detail a system for formulating fatty products, shortenings or special fats, from three or more components by using neural networks (MIX. All stages of development, including design, construction, training, evaluation, and operation of the network will be outlined.
Las redes neuronales son una rama de la inteligencia artificial basadas en la estructura y funcionamiento de sistemas biológicos, teniendo como principal característica la capacidad de aprender y generalizar conocimiento. Estas son utilizadas en la resolución de problemas complejos, en los cuales los sistemas computacionales tradicionales presentan una eficiencia baja. Hasta la fecha, han sido propuestas aplicaciones para los más diversos sectores y actividades. En el área de grasas y aceites, la utilización de redes neuronales se ha concentrado principalmente en dos asuntos: la detección de adulteraciones y la formulación de productos grasos. La formulación de grasas para uso específico es el caso clásico de problema complejo donde un experto o grupo de
[Medical use of artificial neural networks].
Molnár, B; Papik, K; Schaefer, R; Dombóvári, Z; Fehér, J; Tulassay, Z
1998-01-04
The main aim of the research in medical diagnostics is to develop more exact, cost-effective and handsome systems, procedures and methods for supporting the clinicians. In their paper the authors introduce a new method that recently came into the focus referred to as artificial neural networks. Based on the literature of the past 5-6 years they give a brief review--highlighting the most important ones--showing the idea behind neural networks, what they are used for in the medical field. The definition, structure and operation of neural networks are discussed. In the application part they collect examples in order to give an insight in the neural network application research. It is emphasised that in the near future basically new diagnostic equipment can be developed based on this new technology in the field of ECG, EEG and macroscopic and microscopic image analysis systems.
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...
Blood glucose prediction using neural network
Soh, Chit Siang; Zhang, Xiqin; Chen, Jianhong; Raveendran, P.; Soh, Phey Hong; Yeo, Joon Hock
2008-02-01
We used neural network for blood glucose level determination in this study. The data set used in this study was collected using a non-invasive blood glucose monitoring system with six laser diodes, each laser diode operating at distinct near infrared wavelength between 1500nm and 1800nm. The neural network is specifically used to determine blood glucose level of one individual who participated in an oral glucose tolerance test (OGTT) session. Partial least squares regression is also used for blood glucose level determination for the purpose of comparison with the neural network model. The neural network model performs better in the prediction of blood glucose level as compared with the partial least squares model.
Neural Networks in Mobile Robot Motion
Directory of Open Access Journals (Sweden)
Danica Janglová
2004-03-01
Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the “free” space using ultrasound range finder data. The second neural network “finds” a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.
Neural Networks in Mobile Robot Motion
Directory of Open Access Journals (Sweden)
Danica Janglova
2008-11-01
Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the "free" space using ultrasound range finder data. The second neural network "finds" a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.
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.
Constructive autoassociative neural network for facial recognition.
Directory of Open Access Journals (Sweden)
Bruno J T Fernandes
Full Text Available Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network. CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature.
Genetic Algorithm Optimized Neural Networks Ensemble as ...
African Journals Online (AJOL)
NJD
Genetic Algorithm Optimized Neural Networks Ensemble as. Calibration Model for Simultaneous Spectrophotometric. Estimation of Atenolol and Losartan Potassium in Tablets. Dondeti Satyanarayana*, Kamarajan Kannan and Rajappan Manavalan. Department of Pharmacy, Annamalai University, Annamalainagar, Tamil ...
A NEURAL NETWORK BASED IRIS RECOGNITION SYSTEM FOR PERSONAL IDENTIFICATION
Directory of Open Access Journals (Sweden)
Usham Dias
2010-10-01
Full Text Available This paper presents biometric personal identification based on iris recognition using artificial neural networks. Personal identification system consists of localization of the iris region, normalization, enhancement and then iris pattern recognition using neural network. In this paper, through results obtained, we have shown that a person’s left and right eye are unique. In this paper, we also show that the network is sensitive to the initial weights and that over-training gives bad results. We also propose a fast algorithm for the localization of the inner and outer boundaries of the iris region. Results of simulations illustrate the effectiveness of the neural system in personal identification. Finally a hardware iris recognition model is proposed and implementation aspects are discussed.
A novel word spotting method based on recurrent neural networks.
Frinken, Volkmar; Fischer, Andreas; Manmatha, R; Bunke, Horst
2012-02-01
Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperform not only a classical dynamic time warping-based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition.
Dual adaptive dynamic control of mobile robots using neural networks.
Bugeja, Marvin K; Fabri, Simon G; Camilleri, Liberato
2009-02-01
This paper proposes two novel dual adaptive neural control schemes for the dynamic control of nonholonomic mobile robots. The two schemes are developed in discrete time, and the robot's nonlinear dynamic functions are assumed to be unknown. Gaussian radial basis function and sigmoidal multilayer perceptron neural networks are used for function approximation. In each scheme, the unknown network parameters are estimated stochastically in real time, and no preliminary offline neural network training is used. In contrast to other adaptive techniques hitherto proposed in the literature on mobile robots, the dual control laws presented in this paper do not rely on the heuristic certainty equivalence property but account for the uncertainty in the estimates. This results in a major improvement in tracking performance, despite the plant uncertainty and unmodeled dynamics. Monte Carlo simulation and statistical hypothesis testing are used to illustrate the effectiveness of the two proposed stochastic controllers as applied to the trajectory-tracking problem of a differentially driven wheeled mobile robot.
Classifying epilepsy diseases using artificial neural networks and genetic algorithm.
Koçer, Sabri; Canal, M Rahmi
2011-08-01
In this study, FFT analysis is applied to the EEG signals of the normal and patient subjects and the obtained FFT coefficients are used as inputs in Artificial Neural Network (ANN). The differences shown by the non-stationary random signals such as EEG signals in cases of health and sickness (epilepsy) were evaluated and tried to be analyzed under computer-supported conditions by using artificial neural networks. Multi-Layer Perceptron (MLP) architecture is used Levenberg-Marquardt (LM), Quickprop (QP), Delta-bar delta (DBD), Momentum and Conjugate gradient (CG) learning algorithms, and the best performance was tried to be attained by ensuring the optimization with the use of genetic algorithms of the weights, learning rates, neuron numbers of hidden layer in the training process. This study shows that the artificial neural network increases the classification performance using genetic algorithm.
Neural network versus classical time series forecasting models
Nor, Maria Elena; Safuan, Hamizah Mohd; Shab, Noorzehan Fazahiyah Md; Asrul, Mohd; Abdullah, Affendi; Mohamad, Nurul Asmaa Izzati; Lee, Muhammad Hisyam
2017-05-01
Artificial neural network (ANN) has advantage in time series forecasting as it has potential to solve complex forecasting problems. This is because ANN is data driven approach which able to be trained to map past values of a time series. In this study the forecast performance between neural network and classical time series forecasting method namely seasonal autoregressive integrated moving average models was being compared by utilizing gold price data. Moreover, the effect of different data preprocessing on the forecast performance of neural network being examined. The forecast accuracy was evaluated using mean absolute deviation, root mean square error and mean absolute percentage error. It was found that ANN produced the most accurate forecast when Box-Cox transformation was used as data preprocessing.
High solar activity predictions through an artificial neural network
Orozco-Del-Castillo, M. G.; Ortiz-Alemán, J. C.; Couder-Castañeda, C.; Hernández-Gómez, J. J.; Solís-Santomé, A.
The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24-26, which we found to occur before 2040.
Neural-network-based voice-tracking algorithm
Baker, Mary; Stevens, Charise; Chaparro, Brennen; Paschall, Dwayne
2002-11-01
A voice-tracking algorithm was developed and tested for the purposes of electronically separating the voice signals of simultaneous talkers. Many individuals suffer from hearing disorders that often inhibit their ability to focus on a single speaker in a multiple speaker environment (the cocktail party effect). Digital hearing aid technology makes it possible to implement complex algorithms for speech processing in both the time and frequency domains. In this work, an average magnitude difference function (AMDF) was performed on mixed voice signals in order to determine the fundamental frequencies present in the signals. A time prediction neural network was trained to recognize normal human voice inflection patterns, including rising, falling, rising-falling, and falling-rising patterns. The neural network was designed to track the fundamental frequency of a single talker based on the training procedure. The output of the neural network can be used to design an active filter for speaker segregation. Tests were done using audio mixing of two to three speakers uttering short phrases. The AMDF function accurately identified the fundamental frequencies present in the signal. The neural network was tested using a single speaker uttering a short sentence. The network accurately tracked the fundamental frequency of the speaker.
Using neural networks for prediction of nuclear parameters
Energy Technology Data Exchange (ETDEWEB)
Pereira Filho, Leonidas; Souto, Kelling Cabral, E-mail: leonidasmilenium@hotmail.com, E-mail: kcsouto@bol.com.br [Instituto Federal de Educacao, Ciencia e Tecnologia do Rio de Janeiro (IFRJ), Rio de Janeiro, RJ (Brazil); Machado, Marcelo Dornellas, E-mail: dornemd@eletronuclear.gov.br [Eletrobras Termonuclear S.A. (GCN.T/ELETRONUCLEAR), Rio de Janeiro, RJ (Brazil). Gerencia de Combustivel Nuclear
2013-07-01
Dating from 1943, the earliest work on artificial neural networks (ANN), when Warren Mc Cullock and Walter Pitts developed a study on the behavior of the biological neuron, with the goal of creating a mathematical model. Some other work was done until after the 80 witnessed an explosion of interest in ANNs, mainly due to advances in technology, especially microelectronics. Because ANNs are able to solve many problems such as approximation, classification, categorization, prediction and others, they have numerous applications in various areas, including nuclear. Nodal method is adopted as a tool for analyzing core parameters such as boron concentration and pin power peaks for pressurized water reactors. However, this method is extremely slow when it is necessary to perform various core evaluations, for example core reloading optimization. To overcome this difficulty, in this paper a model of Multi-layer Perceptron (MLP) artificial neural network type backpropagation will be trained to predict these values. The main objective of this work is the development of Multi-layer Perceptron (MLP) artificial neural network capable to predict, in very short time, with good accuracy, two important parameters used in the core reloading problem - Boron Concentration and Power Peaking Factor. For the training of the neural networks are provided loading patterns and nuclear data used in cycle 19 of Angra 1 nuclear power plant. Three models of networks are constructed using the same input data and providing the following outputs: 1- Boron Concentration and Power Peaking Factor, 2 - Boron Concentration and 3 - Power Peaking Factor. (author)
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
Neural networks as models of psychopathology.
Aakerlund, L; Hemmingsen, R
1998-04-01
Neural network modeling is situated between neurobiology, cognitive science, and neuropsychology. The structural and functional resemblance with biological computation has made artificial neural networks (ANN) useful for exploring the relationship between neurobiology and computational performance, i.e., cognition and behavior. This review provides an introduction to the theory of ANN and how they have linked theories from neurobiology and psychopathology in schizophrenia, affective disorders, and dementia.
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security
Kang, Min-Joo
2016-01-01
A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus. PMID:27271802
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.
Kang, Min-Joo; Kang, Je-Won
2016-01-01
A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.
Directory of Open Access Journals (Sweden)
Min-Joo Kang
Full Text Available A novel intrusion detection system (IDS using a deep neural network (DNN is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN, therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN bus.
A neural network simulation package in CLIPS
Bhatnagar, Himanshu; Krolak, Patrick D.; Mcgee, Brenda J.; Coleman, John
1990-01-01
The intrinsic similarity between the firing of a rule and the firing of a neuron has been captured in this research to provide a neural network development system within an existing production system (CLIPS). A very important by-product of this research has been the emergence of an integrated technique of using rule based systems in conjunction with the neural networks to solve complex problems. The systems provides a tool kit for an integrated use of the two techniques and is also extendible to accommodate other AI techniques like the semantic networks, connectionist networks, and even the petri nets. This integrated technique can be very useful in solving complex AI problems.
Diabetic retinopathy screening using deep neural network.
Ramachandran, Nishanthan; Hong, Sheng Chiong; Sime, Mary J; Wilson, Graham A
2017-09-07
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. Retrospective audit. 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). Area under the receiver operating characteristic curve, sensitivity and specificity. For detecting referable diabetic retinopathy, the deep neural network had an area under receiver operating characteristic curve of 0.901 (95% confidence interval 0.807-0.995), with 84.6% sensitivity and 79.7% specificity for Otago and 0.980 (95% confidence interval 0.973-0.986), with 96.0% sensitivity and 90.0% specificity for Messidor. 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. © 2017 Royal Australian and New Zealand College of Ophthalmologists.
Regularized negative correlation learning for neural network ensembles.
Chen, Huanhuan; Yao, Xin
2009-12-01
Negative correlation learning (NCL) is a neural network ensemble learning algorithm that introduces a correlation penalty term to the cost function of each individual network so that each neural network minimizes its mean square error (MSE) together with the correlation of the ensemble. This paper analyzes NCL and reveals that the training of NCL (when lambda = 1) corresponds to training the entire ensemble as a single learning machine that only minimizes the MSE without regularization. This analysis explains the reason why NCL is prone to overfitting the noise in the training set. This paper also demonstrates that tuning the correlation parameter lambda in NCL by cross validation cannot overcome the overfitting problem. The paper analyzes this problem and proposes the regularized negative correlation learning (RNCL) algorithm which incorporates an additional regularization term for the whole ensemble. RNCL decomposes the ensemble's training objectives, including MSE and regularization, into a set of sub-objectives, and each sub-objective is implemented by an individual neural network. In this paper, we also provide a Bayesian interpretation for RNCL and provide an automatic algorithm to optimize regularization parameters based on Bayesian inference. The RNCL formulation is applicable to any nonlinear estimator minimizing the MSE. The experiments on synthetic as well as real-world data sets demonstrate that RNCL achieves better performance than NCL, especially when the noise level is nontrivial in the data set.
Design of Jetty Piles Using Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Yongjei Lee
2014-01-01
Full Text Available To overcome the complication of jetty pile design process, artificial neural networks (ANN are adopted. To generate the training samples for training ANN, finite element (FE analysis was performed 50 times for 50 different design cases. The trained ANN was verified with another FE analysis case and then used as a structural analyzer. The multilayer neural network (MBPNN with two hidden layers was used for ANN. The framework of MBPNN was defined as the input with the lateral forces on the jetty structure and the type of piles and the output with the stress ratio of the piles. The results from the MBPNN agree well with those from FE analysis. Particularly for more complex modes with hundreds of different design cases, the MBPNN would possibly substitute parametric studies with FE analysis saving design time and cost.
Process identification through modular neural networks and rule extraction (extended abstract)
van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.; Blockeel, Hendrik; Denecker, Marc
2002-01-01
Monolithic neural networks may be trained from measured data to establish knowledge about the process. Unfortunately, this knowledge is not guaranteed to be found and – if at all – hard to extract. Modular neural networks are better suited for this purpose. Domain-ordered by topology, rule
Using domain-specific basic functions for the analysis of supervised artificial neural networks
van der Zwaag, B.J.
2003-01-01
Since the early development of artificial neural networks, researchers have tried to analyze trained neural networks in order to gain insight into their behavior. For certain applications and in certain problem domains this has been successful, for example by the development of so-called rule
Classifying Symmetrical Differences and Temporal Change in Mammography Using Deep Neural Networks
Kooi, T.; Karssemeijer, N.
2017-01-01
Neural networks, in particular deep Convolutional Neural Networks (CNN), have recently gone through a renaissance sparked by the introduction of more efficient training procedures and massive amounts of raw annotated data. Barring a handful of modalities, medical images are typically too large to
Peng, Yefei
2010-01-01
An ontology mapping neural network (OMNN) is proposed in order to learn and infer correspondences among ontologies. It extends the Identical Elements Neural Network (IENN)'s ability to represent and map complex relationships. The learning dynamics of simultaneous (interlaced) training of similar tasks interact at the shared connections of the…
Identifying apple surface defects using principal components analysis and artifical neural networks
Artificial neural networks and principal components were used to detect surface defects on apples in near-infrared images. Neural networks were trained and tested on sets of principal components derived from columns of pixels from images of apples acquired at two wavelengths (740 nm and 950 nm). I...
Transient stability analysis of electric energy systems via a fuzzy ART-ARTMAP neural network
Energy Technology Data Exchange (ETDEWEB)
Ferreira, Wagner Peron; Silveira, Maria do Carmo G.; Lotufo, AnnaDiva P.; Minussi, Carlos. R. [Department of Electrical Engineering, Sao Paulo State University (UNESP), P.O. Box 31, 15385-000, Ilha Solteira, SP (Brazil)
2006-04-15
This work presents a methodology to analyze transient stability (first oscillation) of electric energy systems, using a neural network based on ART architecture (adaptive resonance theory), named fuzzy ART-ARTMAP neural network for real time applications. The security margin is used as a stability analysis criterion, considering three-phase short circuit faults with a transmission line outage. The neural network operation consists of two fundamental phases: the training and the analysis. The training phase needs a great quantity of processing for the realization, while the analysis phase is effectuated almost without computation effort. This is, therefore the principal purpose to use neural networks for solving complex problems that need fast solutions, as the applications in real time. The ART neural networks have as primordial characteristics the plasticity and the stability, which are essential qualities to the training execution and to an efficient analysis. The fuzzy ART-ARTMAP neural network is proposed seeking a superior performance, in terms of precision and speed, when compared to conventional ARTMAP, and much more when compared to the neural networks that use the training by backpropagation algorithm, which is a benchmark in neural network area. (author)
Symbolic processing in neural networks
Neto, João Pedro; Hava T Siegelmann; Costa,J.Félix
2003-01-01
In this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only theoretical exciting, but has also some practical implications in the recent efforts to merge symbolic and sub symbolic computation. To be of some use, it should be carried in a context of bounded resources. Herein, we show how to use resource bounds to speed up computations over neural nets, thro...
Generating three-qubit quantum circuits with neural networks
Swaddle, Michael; Noakes, Lyle; Smallbone, Harry; Salter, Liam; Wang, Jingbo
2017-10-01
A new method for compiling quantum algorithms is proposed and tested for a three qubit system. The proposed method is to decompose a unitary matrix U, into a product of simpler Uj via a neural network. These Uj can then be decomposed into product of known quantum gates. Key to the effectiveness of this approach is the restriction of the set of training data generated to paths which approximate minimal normal subRiemannian geodesics, as this removes unnecessary redundancy and ensures the products are unique. The two neural networks are shown to work effectively, each individually returning low loss values on validation data after relatively short training periods. The two networks are able to return coefficients that are sufficiently close to the true coefficient values to validate this method as an approach for generating quantum circuits. There is scope for more work in scaling this approach for larger quantum systems.
Hindcasting cyclonic waves using neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Rao, S.; Chakravarty, N.V.
the backpropagation networks with updated algorithms are used in this paper. A brief description about the working of a back propagation neural network and three updated algorithms is given below. Backpropagation learning: Backpropagation is the most widely used... algorithm for supervised learning with multi layer feed forward networks. The idea of the backpropagation learning algorithm is the repeated application of the chain rule to compute the influence of each weight in the network with respect to an arbitrary...
Probing many-body localization with neural networks
Schindler, Frank; Regnault, Nicolas; Neupert, Titus
2017-06-01
We show that a simple artificial neural network trained on entanglement spectra of individual states of a many-body quantum system can be used to determine the transition between a many-body localized and a thermalizing regime. Specifically, we study the Heisenberg spin-1/2 chain in a random external field. We employ a multilayer perceptron with a single hidden layer, which is trained on labeled entanglement spectra pertaining to the fully localized and fully thermal regimes. We then apply this network to classify spectra belonging to states in the transition region. For training, we use a cost function that contains, in addition to the usual error and regularization parts, a term that favors a confident classification of the transition region states. The resulting phase diagram is in good agreement with the one obtained by more conventional methods and can be computed for small systems. In particular, the neural network outperforms conventional methods in classifying individual eigenstates pertaining to a single disorder realization. It allows us to map out the structure of these eigenstates across the transition with spatial resolution. Furthermore, we analyze the network operation using the dreaming technique to show that the neural network correctly learns by itself the power-law structure of the entanglement spectra in the many-body localized regime.
Application of neural networks to waste site screening
Energy Technology Data Exchange (ETDEWEB)
Dabiri, A.E.; Garrett, M.; Kraft, T.; Hilton, J.; VanHammersveld, M.
1993-02-01
Waste site screening requires knowledge of the actual concentrations of hazardous materials and rates of flow around and below the site with time. The present approach consists primarily of drilling boreholes near contaminated sites and chemically analyzing the extracted physical samples and processing the data. This is expensive and time consuming. The feasibility of using neural network techniques to reduce the cost of waste site screening was investigated. Two neural network techniques, gradient descent back propagation and fully recurrent back propagation were utilized. The networks were trained with data received from Westinghouse Hanford Corporation. The results indicate that the network trained with the fully recurrent technique shows satisfactory generalization capability. The predicted results are close to the results obtained from a mathematical flow prediction model. It is possible to develop a new tool to predict the waste plume, thus substantially reducing the number of the bore sites and samplings. There are a variety of applications for this technique in environmental site screening and remediation. One of the obvious applications would be for optimum well siting. A neural network trained from the existing sampling data could be utilized to decide where would be the best position for the next bore site. Other applications are discussed in the report.
A Model for Improving the Learning Curves of Artificial Neural Networks.
Directory of Open Access Journals (Sweden)
Roberto L S Monteiro
Full Text Available In this article, the performance of a hybrid artificial neural network (i.e. scale-free and small-world was analyzed and its learning curve compared to three other topologies: random, scale-free and small-world, as well as to the chemotaxis neural network of the nematode Caenorhabditis Elegans. One hundred equivalent networks (same number of vertices and average degree for each topology were generated and each was trained for one thousand epochs. After comparing the mean learning curves of each network topology with the C. elegans neural network, we found that the networks that exhibited preferential attachment exhibited the best learning curves.
Regional Computation of TEC Using a Neural Network Model
Leandro, R. F.; Santos, M. C.
2004-05-01
One of the main sources of errors of GPS measurements is the ionosphere refraction. As a dispersive medium, the ionosphere allow its influence to be computed by using dual frequency receivers. In the case of single frequency receivers it is necessary to use models that tell us how big the ionospheric refraction is. The GPS broadcast message carries parameters of this model, namely Klobuchar model. Dual frequency receivers allow to estimate the influence of ionosphere in the GPS signal by the computation of TEC (Total Electron Content) values, that have a direct relationship with the magnitude of the delay caused by the ionosphere. One alternative is to create a regional model based on a network of dual frequency receivers. In this case, the regional behaviour of ionosphere is modelled in a way that it is possible to estimate the TEC values into or near this region. This regional model can be based on polynomials, for example. In this work we will present a Neural Network-based model to the regional computation of TEC. The advantage of using a Neural Network is that it is not necessary to have a great knowledge on the behaviour of the modelled surface due to the adaptation capability of neural networks training process, that is an iterative adjust of the synaptic weights in function of residuals, using the training parameters. Therefore, the previous knowledge of the modelled phenomena is important to define what kind of and how many parameters are needed to train the neural network so that reasonable results are obtained from the estimations. We have used data from the GPS tracking network in Brazil, and we have tested the accuracy of the new model to all locations where there is a station, accessing the efficiency of the model everywhere. TEC values were computed for each station of the network. After that the training parameters data set for the test station was formed, with the TEC values of all others (all stations, except the test one). The Neural Network was
Decorrelated jet substructure tagging using adversarial neural networks
Shimmin, Chase; Sadowski, Peter; Baldi, Pierre; Weik, Edison; Whiteson, Daniel; Goul, Edward; Søgaard, Andreas
2017-10-01
We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved discovery significance relative to existing taggers. The network is trained using an adversarial strategy, resulting in a tagger that learns to balance classification accuracy with decorrelation. As a benchmark scenario, we consider the case where large-radius jets originating from a boosted resonance decay are discriminated from a background of nonresonant quark and gluon jets. We show that in the presence of systematic uncertainties on the background rate, our adversarially trained, decorrelated tagger considerably outperforms a conventionally trained neural network, despite having a slightly worse signal-background separation power. We generalize the adversarial training technique to include a parametric dependence on the signal hypothesis, training a single network that provides optimized, interpolatable decorrelated jet tagging across a continuous range of hypothetical resonance masses, after training on discrete choices of the signal mass.
Identification of the non-linear systems using internal recurrent neural networks
Directory of Open Access Journals (Sweden)
Bogdan CODRES
2006-12-01
Full Text Available In the past years utilization of neural networks took a distinct ampleness because of the following properties: distributed representation of information, capacity of generalization in case of uncontained situation in training data set, tolerance to noise, resistance to partial destruction, parallel processing. Another major advantage of neural networks is that they allow us to obtain the model of the investigated system, systems that is not necessarily to be linear. In fact, the true value of neural networks is seen in the case of identification and control of nonlinear systems. In this paper there are presented some identification techniques using neural networks.
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.
Positive train control shared network.
2015-05-01
The Interoperable Train Control (ITC) Positive : Train Control (PTC) Shared Network (IPSN) : project investigated anticipated industry benefits : and the level of support for the development of : a hosted technological platform for PTC : messaging ac...
Parametric Identification of Aircraft Loads: An Artificial Neural Network Approach
2016-03-30
Undergraduate Student Paper Postgraduate Student Paper Parametric Identification of Aircraft Loads: An Artificial Neural Network Approach...monitoring, flight parameter, nonlinear modeling, Artificial Neural Network , typical loadcase. Introduction Aircraft load monitoring is an... Neural Networks (ANN), i.e. the BP network and Kohonen Clustering Network , are applied and revised by Kalman Filter and Genetic Algorithm to build
Prediction of coal slurry concentration based on artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Zhou, J.; Li, Y.; Cheng, J.; Zhou, Z.; Li, S.; Liu, J.; Cen, K. [Zhejiang University, Hangzhou (China)
2005-12-15
Based on experimental data of coal slurry, three BP neural network models with 8, 7 and 5 input factors, were set up for predicting the slurry concentration. Three BP neural networks algorithm was Levenberg Marquardt algorithm, and their learning rate was 0.01. The hidden neurons number was settled by practical training effect of the networks. The hidden neurons number of BP model, with 8, 7 and 5 input factors is 27, 30 and 24, respectively. Two data treated methods were tested by seven input factors network model, which proves that the first method is the better one. The mean absolute error of the neural network models with 5, 7 and 8 factors is 0.53%, 0.50% and 0.74%, respectively, while that of the existed regression model is 1.15%. This indicates that the neural network models, especially the 7 factors model, are effective in predicting the slurry. The HGI input neuron in eight input factors model affects the prediction result because of its interference to other input factors. The effect of H and N in coal on the slurry is slight. 8 refs., 7 figs., 3 tabs.
High-dimensional multispectral image fusion: classification by neural network
He, Mingyi; Xia, Jiantao
2003-06-01
Advances in sensor technology for Earth observation make it possible to collect multispectral data in much higher dimensionality. Such high dimensional data will it possible to classify more classes. However, it will also have several impacts on processing technology. First, because of its huge data, more processing power will be needed to process such high dimensional data. Second, because of its high dimensionality and the limited training samples, it is very difficult for Bayes method to estimate the parameters accurately. So the classification accuracy cannot be high enough. Neural Network is an intelligent signal processing method. MLFNN (Multi-Layer Feedforward Neural Network) directly learn from training samples and the probability model needs not to be estimated, the classification may be conducted through neural network fusion of multispectral images. The latent information about different classes can be extracted from training samples by MLFNN. However, because of the huge data and high dimensionality, MLFNN will face some serious difficulties: (1) There are many local minimal points in the error surface of MLFNN; (2) Over-fitting phenomena. These two difficulties depress the classification accuracy and generalization performance of MLFNN. In order to overcome these difficulties, the author proposed DPFNN (Double Parallel Feedforward Neural Networks) used to classify the high dimensional multispectral images. The model and learning algorithm of DPFNN with strong generalization performance are proposed, with emphases on the regularization of output weights and improvement of the generalization performance of DPFNN. As DPFNN is composed of MLFNN and SLFNN (Single-Layer Feedforward Neural Network), it has the advantages of MLFNN and SLFNN: (1) Good nonlinear mapping capability; (2) High learning speed for linear-like problem. Experimental results with generated data, 64-band practical multispectral images and 220-band multispectral images show that the new
Extracting rules from neural networks as decision diagrams.
Chorowski, Jan; Zurada, Jacek M
2011-12-01
Rule extraction from neural networks (NNs) solves two fundamental problems: it gives insight into the logic behind the network and in many cases, it improves the network's ability to generalize the acquired knowledge. This paper presents a novel eclectic approach to rule extraction from NNs, named LOcal Rule Extraction (LORE), suited for multilayer perceptron networks with discrete (logical or categorical) inputs. The extracted rules mimic network behavior on the training set and relax this condition on the remaining input space. First, a multilayer perceptron network is trained under standard regime. It is then transformed into an equivalent form, returning the same numerical result as the original network, yet being able to produce rules generalizing the network output for cases similar to a given input. The partial rules extracted for every training set sample are then merged to form a decision diagram (DD) from which logic rules can be extracted. A rule format explicitly separating subsets of inputs for which an answer is known from those with an undetermined answer is presented. A special data structure, the decision diagram, allowing efficient partial rule merging is introduced. With regard to rules' complexity and generalization abilities, LORE gives results comparable to those reported previously. An algorithm transforming DDs into interpretable boolean expressions is described. Experimental running times of rule extraction are proportional to the network's training time.
Bayesian Recurrent Neural Network for Language Modeling.
Chien, Jen-Tzung; Ku, Yuan-Chu
2016-02-01
A language model (LM) is calculated as the probability of a word sequence that provides the solution to word prediction for a variety of information systems. A recurrent neural network (RNN) is powerful to learn the large-span dynamics of a word sequence in the continuous space. However, the training of the RNN-LM is an ill-posed problem because of too many parameters from a large dictionary size and a high-dimensional hidden layer. This paper presents a Bayesian approach to regularize the RNN-LM and apply it for continuous speech recognition. We aim to penalize the too complicated RNN-LM by compensating for the uncertainty of the estimated model parameters, which is represented by a Gaussian prior. The objective function in a Bayesian classification network is formed as the regularized cross-entropy error function. The regularized model is constructed not only by calculating the regularized parameters according to the maximum a posteriori criterion but also by estimating the Gaussian hyperparameter by maximizing the marginal likelihood. A rapid approximation to a Hessian matrix is developed to implement the Bayesian RNN-LM (BRNN-LM) by selecting a small set of salient outer-products. The proposed BRNN-LM achieves a sparser model than the RNN-LM. Experiments on different corpora show the robustness of system performance by applying the rapid BRNN-LM under different conditions.
Prototype-Incorporated Emotional Neural Network.
Oyedotun, Oyebade K; Khashman, Adnan
2017-08-15
Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.
On sparsely connected optimal neural networks
Energy Technology Data Exchange (ETDEWEB)
Beiu, V. [Los Alamos National Lab., NM (United States); Draghici, S. [Wayne State Univ., Detroit, MI (United States)
1997-10-01
This paper uses two different approaches to show that VLSI- and size-optimal discrete neural networks are obtained for small fan-in values. These have applications to hardware implementations of neural networks, but also reveal an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures. The first approach is based on implementing F{sub n,m} functions. The authors 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. In order to estimate the area (A) and the delay (T) of such networks, the following cost functions will be used: (i) the connectivity and the number-of-bits for representing the weights and thresholds--for good estimates of the area; and (ii) the fan-ins and the length of the wires--for good approximates of the delay. 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 the size of fan-in 2 neural networks. They will generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan-in values. Finally, a size-optimal neural network of small constant fan-ins will be suggested for F{sub n,m} functions.
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...
Markov Chain Monte Carlo Bayesian Learning for Neural Networks
Goodrich, Michael S.
2011-01-01
Conventional training methods for neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g., normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available data and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in network weights and therefore network predictions by using a modified Jeffery's prior combined with a Metropolis Markov Chain Monte Carlo method.
Visual Servoing from Deep Neural Networks
Bateux, Quentin; Marchand, Eric; Leitner, Jürgen; Chaumette, Francois; Corke, Peter
2017-01-01
International audience; We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF visual servoing. The paper describes how to create a dataset simulating various perturbations (occlusions and lighting conditions) from a single real-world image of the scene. A convolutional neural network is fine-tuned using this dataset to estimate the relative pose between two images of the same scene. The output of the network is then employed in a visual servoing c...
Design of Robust Neural Network Classifiers
DEFF Research Database (Denmark)
Larsen, Jan; Andersen, Lars Nonboe; Hintz-Madsen, Mads
1998-01-01
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...... 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...
Electronic device aspects of neural network memories
Lambe, J.; Moopenn, A.; Thakoor, A. P.
1985-01-01
The basic issues related to the electronic implementation of the neural network model (NNM) for content addressable memories are examined. A brief introduction to the principles of the NNM is followed by an analysis of the information storage of the neural network in the form of a binary connection matrix and the recall capability of such matrix memories based on a hardware simulation study. In addition, materials and device architecture issues involved in the future realization of such networks in VLSI-compatible ultrahigh-density memories are considered. A possible space application of such devices would be in the area of large-scale information storage without mechanical devices.
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.
Plant species classification using deep convolutional neural network
DEFF Research Database (Denmark)
Dyrmann, Mads; Karstoft, Henrik; Midtiby, Henrik Skov
2016-01-01
Information on which weed species are present within agricultural fields is important for site specific weed management. This paper presents a method that is capable of recognising plant species in colour images by using a convolutional neural network. The network is built from scratch trained...... stabilisation and illumination, and images shot with hand-held mobile phones in fields with changing lighting conditions and different soil types. For these 22 species, the network is able to achieve a classification accuracy of 86.2%....
Statistical modelling of neural networks in {gamma}-spectrometry applications
Energy Technology Data Exchange (ETDEWEB)
Vigneron, V.; Martinez, J.M. [CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France). Dept. de Mecanique et de Technologie; Morel, J.; Lepy, M.C. [CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France). Dept. des Applications et de la Metrologie des Rayonnements Ionisants
1995-12-31
Layered Neural Networks, which are a class of models based on neural computation, are applied to the measurement of uranium enrichment, i.e. the isotope ratio {sup 235} U/({sup 235} U + {sup 236} U + {sup 238} U). The usual method consider a limited number of {Gamma}-ray and X-ray peaks, and require previously calibrated instrumentation for each sample. But, in practice, the source-detector ensemble geometry conditions are critically different, thus a means of improving the above convention methods is to reduce the region of interest: this is possible by focusing on the K{sub {alpha}} X region where the three elementary components are present. Real data are used to study the performance of neural networks. Training is done with a Maximum Likelihood method to measure uranium {sup 235} U and {sup 238} U quantities in infinitely thick samples. (authors). 18 refs., 6 figs., 3 tabs.
Human Parsing with Contextualized Convolutional Neural Network.
Liang, Xiaodan; Xu, Chunyan; Shen, Xiaohui; Yang, Jianchao; Tang, Jinhui; Lin, Liang; Yan, Shuicheng
2016-03-02
In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, semantic edge context, within-super-pixel context and cross-super-pixel neighborhood context into a unified network. Given an input human image, Co-CNN produces the pixel-wise categorization in an end-to-end way. First, the cross-layer context is captured by our basic local-to-global-to-local structure, which hierarchically combines the global semantic information and the local fine details across different convolutional layers. Second, the global image-level label prediction is used as an auxiliary objective in the intermediate layer of the Co-CNN, and its outputs are further used for guiding the feature learning in subsequent convolutional layers to leverage the global imagelevel context. Third, semantic edge context is further incorporated into Co-CNN, where the high-level semantic boundaries are leveraged to guide pixel-wise labeling. Finally, to further utilize the local super-pixel contexts, the within-super-pixel smoothing and cross-super-pixel neighbourhood voting are formulated as natural sub-components of the Co-CNN to achieve the local label consistency in both training and testing process. Comprehensive evaluations on two public datasets well demonstrate the significant superiority of our Co-CNN over other state-of-the-arts for human parsing. In particular, the F-1 score on the large dataset [1] reaches 81:72% by Co-CNN, significantly higher than 62:81% and 64:38% by the state-of-the-art algorithms, MCNN [2] and ATR [1], respectively. By utilizing our newly collected large dataset for training, our Co-CNN can achieve 85:36% in F-1 score.
Predictive Control of Hydronic Floor Heating Systems using Neural Networks and Genetic Algorithms
DEFF Research Database (Denmark)
Vinther, Kasper; Green, Torben; Østergaard, Søren
2017-01-01
This paper presents the use a neural network and a micro genetic algorithm to optimize future set-points in existing hydronic floor heating systems for improved energy efficiency. The neural network can be trained to predict the impact of changes in set-points on future room temperatures. Additio...... space is not guaranteed. Evaluation of the performance of multiple neural networks is performed, using different levels of information, and optimization results are presented on a detailed house simulation model.......This paper presents the use a neural network and a micro genetic algorithm to optimize future set-points in existing hydronic floor heating systems for improved energy efficiency. The neural network can be trained to predict the impact of changes in set-points on future room temperatures...
Sea level forecasts using neural networks
Röske, Frank
1997-03-01
In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the
Antagonistic neural networks underlying differentiated leadership roles
Richard Eleftherios Boyatzis; Kylie eRochford; Anthony Ian Jack
2014-01-01
The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950’s. Recent research in neuroscience suggests that the division between task oriented and socio-emotional oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks -- the Task Positive Network (TPN) and the Default Mode Network (DMN). Neural activity in ...
Model-Based Fault Diagnosis in Electric Drive Inverters Using Artificial Neural Network
National Research Council Canada - National Science Library
Masrur, Abul; Chen, ZhiHang; Zhang, Baifang; Jia, Hongbin; Murphey, Yi-Lu
2006-01-01
.... A normal model and various faulted models of the inverter-motor combination were developed, and voltages and current signals were generated from those models to train an artificial neural network for fault diagnosis...
PERFORMANCE COMPARISON FOR INTRUSION DETECTION SYSTEM USING NEURAL NETWORK WITH KDD DATASET
Directory of Open Access Journals (Sweden)
S. Devaraju
2014-04-01
Full Text Available Intrusion Detection Systems are challenging task for finding the user as normal user or attack user in any organizational information systems or IT Industry. The Intrusion Detection System is an effective method to deal with the kinds of problem in networks. Different classifiers are used to detect the different kinds of attacks in networks. In this paper, the performance of intrusion detection is compared with various neural network classifiers. In the proposed research the four types of classifiers used are Feed Forward Neural Network (FFNN, Generalized Regression Neural Network (GRNN, Probabilistic Neural Network (PNN and Radial Basis Neural Network (RBNN. The performance of the full featured KDD Cup 1999 dataset is compared with that of the reduced featured KDD Cup 1999 dataset. The MATLAB software is used to train and test the dataset and the efficiency and False Alarm Rate is measured. It is proved that the reduced dataset is performing better than the full featured dataset.
Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Ziaul Huque
2007-08-31
This is the final technical report for the project titled 'Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks'. The aim of the project was to develop an efficient chemistry model for combustion simulations. The reduced chemistry model was developed mathematically without the need of having extensive knowledge of the chemistry involved. To aid in the development of the model, Neural Networks (NN) was used via a new network topology known as Non-linear Principal Components Analysis (NPCA). A commonly used Multilayer Perceptron Neural Network (MLP-NN) was modified to implement NPCA-NN. The training rate of NPCA-NN was improved with the GEneralized Regression Neural Network (GRNN) based on kernel smoothing techniques. Kernel smoothing provides a simple way of finding structure in data set without the imposition of a parametric model. The trajectory data of the reaction mechanism was generated based on the optimization techniques of genetic algorithm (GA). The NPCA-NN algorithm was then used for the reduction of Dimethyl Ether (DME) mechanism. DME is a recently discovered fuel made from natural gas, (and other feedstock such as coal, biomass, and urban wastes) which can be used in compression ignition engines as a substitute for diesel. An in-house two-dimensional Computational Fluid Dynamics (CFD) code was developed based on Meshfree technique and time marching solution algorithm. The project also provided valuable research experience to two graduate students.
Constructing general partial differential equations using polynomial and neural networks.
Zjavka, Ladislav; Pedrycz, Witold
2016-01-01
Sum fraction terms can approximate multi-variable functions on the basis of discrete observations, replacing a partial differential equation definition with polynomial elementary data relation descriptions. Artificial neural networks commonly transform the weighted sum of inputs to describe overall similarity relationships of trained and new testing input patterns. Differential polynomial neural networks form a new class of neural networks, which construct and solve an unknown general partial differential equation of a function of interest with selected substitution relative terms using non-linear multi-variable composite polynomials. The layers of the network generate simple and composite relative substitution terms whose convergent series combinations can describe partial dependent derivative changes of the input variables. This regression is based on trained generalized partial derivative data relations, decomposed into a multi-layer polynomial network structure. The sigmoidal function, commonly used as a nonlinear activation of artificial neurons, may transform some polynomial items together with the parameters with the aim to improve the polynomial derivative term series ability to approximate complicated periodic functions, as simple low order polynomials are not able to fully make up for the complete cycles. The similarity analysis facilitates substitutions for differential equations or can form dimensional units from data samples to describe real-world problems. Copyright © 2015 Elsevier Ltd. All rights reserved.
Static Voltage Stability Analysis by Using SVM and Neural Network
Directory of Open Access Journals (Sweden)
Mehdi Hajian
2013-01-01
Full Text Available Voltage stability is an important problem in power system networks. In this paper, in terms of static voltage stability, and application of Neural Networks (NN and Supported Vector Machine (SVM for estimating of voltage stability margin (VSM and predicting of voltage collapse has been investigated. This paper considers voltage stability in power system in two parts. The first part calculates static voltage stability margin by Radial Basis Function Neural Network (RBFNN. The advantage of the used method is high accuracy in online detecting the VSM. Whereas the second one, voltage collapse analysis of power system is performed by Probabilistic Neural Network (PNN and SVM. The obtained results in this paper indicate, that time and number of training samples of SVM, are less than NN. In this paper, a new model of training samples for detection system, using the normal distribution load curve at each load feeder, has been used. Voltage stability analysis is estimated by well-know L and VSM indexes. To demonstrate the validity of the proposed methods, IEEE 14 bus grid and the actual network of Yazd Province are used.
Neural network signal understanding for instrumentation
DEFF Research Database (Denmark)
Pau, L. F.; Johansen, F. S.
1990-01-01
A report is presented on the use of neural signal interpretation theory and techniques for the purpose of classifying the shapes of a set of instrumentation signals, in order to calibrate devices, diagnose anomalies, generate tuning/settings, and interpret the measurement results. Neural signal...... understanding research is surveyed, and the selected implementation and its performance in terms of correct classification rates and robustness to noise are described. Formal results on neural net training time and sensitivity to weights are given. A theory for neural control using functional link nets is given......, and an explanation facility designed to help neural signal understanding is described. The results are compared to those obtained with a knowledge-based signal interpretation system using the same instrument and data...
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.
Decorrelation of Neural-Network Activity by Inhibitory Feedback
Einevoll, Gaute T.; Diesmann, Markus
2012-01-01
Correlations in spike-train ensembles can seriously impair the encoding of information by their spatio-temporal structure. An inevitable source of correlation in finite neural networks is common presynaptic input to pairs of neurons. Recent studies demonstrate that spike correlations in recurrent neural networks are considerably smaller than expected based on the amount of shared presynaptic input. Here, we explain this observation by means of a linear network model and simulations of networks of leaky integrate-and-fire neurons. We show that inhibitory feedback efficiently suppresses pairwise correlations and, hence, population-rate fluctuations, thereby assigning inhibitory neurons the new role of active decorrelation. We quantify this decorrelation by comparing the responses of the intact recurrent network (feedback system) and systems where the statistics of the feedback channel is perturbed (feedforward system). Manipulations of the feedback statistics can lead to a significant increase in the power and coherence of the population response. In particular, neglecting correlations within the ensemble of feedback channels or between the external stimulus and the feedback amplifies population-rate fluctuations by orders of magnitude. The fluctuation suppression in homogeneous inhibitory networks is explained by a negative feedback loop in the one-dimensional dynamics of the compound activity. Similarly, a change of coordinates exposes an effective negative feedback loop in the compound dynamics of stable excitatory-inhibitory networks. The suppression of input correlations in finite networks is explained by the population averaged correlations in the linear network model: In purely inhibitory networks, shared-input correlations are canceled by negative spike-train correlations. In excitatory-inhibitory networks, spike-train correlations are typically positive. Here, the suppression of input correlations is not a result of the mere existence of correlations between
Use of Neural Networks for Damage Assessment in a Steel Mast
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
1994-01-01
excitation. The basic idea is to train a neural network with simulated patterns of the relative changes in natural frequencies and corresponding sizes and locations of damages in order to recognize the behaviour of the damaged as well as the undamaged structure. Subjecting this trained neural network...... bolted joint consists of 4 slice plates giving the possibilities of simulating a 1/4, 1/2, 3/4 and full reduction of the area of a diagonal. A damage is simulated by removing one or more splice plates in these bolted joints. The utility of the neural network approach is demonstrated by a simulation study...... as well as full-scale tests where the mast is identified by an ARMA-model. The results show that a neural network trained with simulated data is capable for detecting location of a damage in a steel lattice mast when the network is subjected to experimental data.·...
Solving differential equations with unknown constitutive relations as recurrent neural networks
Energy Technology Data Exchange (ETDEWEB)
Hagge, Tobias J.; Stinis, Panagiotis; Yeung, Enoch H.; Tartakovsky, Alexandre M.
2017-12-08
We solve a system of ordinary differential equations with an unknown functional form of a sink (reaction rate) term. We assume that the measurements (time series) of state variables are partially available, and use a recurrent neural network to “learn” the reaction rate from this data. This is achieved by including discretized ordinary differential equations as part of a recurrent neural network training problem. We extend TensorFlow’s recurrent neural network architecture to create a simple but scalable and effective solver for the unknown functions, and apply it to a fedbatch bioreactor simulation problem. Use of techniques from recent deep learning literature enables training of functions with behavior manifesting over thousands of time steps. Our networks are structurally similar to recurrent neural networks, but differ in purpose, and require modified training strategies.
Galeazzi, Juan M; Navajas, Joaquín; Mender, Bedeho M W; Quian Quiroga, Rodrigo; Minini, Loredana; Stringer, Simon M
2016-01-01
Neurons have been found in the primate brain that respond to objects in specific locations in hand-centered coordinates. A key theoretical challenge is to explain how such hand-centered neuronal responses may develop through visual experience. In this paper we show how hand-centered visual receptive fields can develop using an artificial neural network model, VisNet, of the primate visual system when driven by gaze changes recorded from human test subjects as they completed a jigsaw. A camera mounted on the head captured images of the hand and jigsaw, while eye movements were recorded using an eye-tracking device. This combination of data allowed us to reconstruct the retinal images seen as humans undertook the jigsaw task. These retinal images were then fed into the neural network model during self-organization of its synaptic connectivity using a biologically plausible trace learning rule. A trace learning mechanism encourages neurons in the model to learn to respond to input images that tend to occur in close temporal proximity. In the data recorded from human subjects, we found that the participant's gaze often shifted through a sequence of locations around a fixed spatial configuration of the hand and one of the jigsaw pieces. In this case, trace learning should bind these retinal images together onto the same subset of output neurons. The simulation results consequently confirmed that some cells learned to respond selectively to the hand and a jigsaw piece in a fixed spatial configuration across different retinal views.
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.
Neural networks for the prediction organic chemistry reactions
Wei, Jennifer N; Aspuru-Guzik, Alán
2016-01-01
Reaction prediction remains one of the great challenges for organic chemistry. Solving this problem computationally requires the programming of a vast amount of knowledge and intuition of the rules of organic chemistry and the development of algorithms for their application. It is desirable to develop algorithms that, like humans, "learn" from being exposed to examples of the application of the rules of organic chemistry. In this work, we introduce a novel algorithm for predicting the products of organic chemistry reactions using machine learning to first identify the reaction type. In particular, we trained deep convolutional neural networks to predict the outcome of reactions based example reactions, using a new reaction fingerprint model. Due to the flexibility of neural networks, the system can attempt to predict reactions outside the domain where it was trained. We test this capability on problems from a popular organic chemistry textbook.
Recursive Bayesian recurrent neural networks for time-series modeling.
Mirikitani, Derrick T; Nikolaev, Nikolay
2010-02-01
This paper develops a probabilistic approach to recursive second-order training of recurrent neural networks (RNNs) for improved time-series modeling. A general recursive Bayesian Levenberg-Marquardt algorithm is derived to sequentially update the weights and the covariance (Hessian) matrix. The main strengths of the approach are a principled handling of the regularization hyperparameters that leads to better generalization, and stable numerical performance. The framework involves the adaptation of a noise hyperparameter and local weight prior hyperparameters, which represent the noise in the data and the uncertainties in the model parameters. Experimental investigations using artificial and real-world data sets show that RNNs equipped with the proposed approach outperform standard real-time recurrent learning and extended Kalman training algorithms for recurrent networks, as well as other contemporary nonlinear neural models, on time-series modeling.
Self-Taught convolutional neural networks for short text clustering.
Xu, Jiaming; Xu, Bo; Wang, Peng; Zheng, Suncong; Tian, Guanhua; Zhao, Jun; Xu, Bo
2017-04-01
Short text clustering is a challenging problem due to its sparseness of text representation. Here we propose a flexible Self-Taught Convolutional neural network framework for Short Text Clustering (dubbed STC(2)), which can flexibly and successfully incorporate more useful semantic features and learn non-biased deep text representation in an unsupervised manner. In our framework, the original raw text features are firstly embedded into compact binary codes by using one existing unsupervised dimensionality reduction method. Then, word embeddings are explored and fed into convolutional neural networks to learn deep feature representations, meanwhile the output units are used to fit the pre-trained binary codes in the training process. Finally, we get the optimal clusters by employing K-means to cluster the learned representations. Extensive experimental results demonstrate that the proposed framework is effective, flexible and outperform several popular clustering methods when tested on three public short text datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.
Chemical-induced disease relation extraction via convolutional neural network.
Gu, Jinghang; Sun, Fuqing; Qian, Longhua; Zhou, Guodong
2017-01-01
This article describes our work on the BioCreative-V chemical-disease relation (CDR) extraction task, which employed a maximum entropy (ME) model and a convolutional neural network model for relation extraction at inter- and intra-sentence level, respectively. In our work, relation extraction between entity concepts in documents was simplified to relation extraction between entity mentions. We first constructed pairs of chemical and disease mentions as relation instances for training and testing stages, then we trained and applied the ME model and the convolutional neural network model for inter- and intra-sentence level, respectively. Finally, we merged the classification results from mention level to document level to acquire the final relations between chemical and disease concepts. The evaluation on the BioCreative-V CDR corpus shows the effectiveness of our proposed approach. http://www.biocreative.org/resources/corpora/biocreative-v-cdr-corpus/.
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
Capacitive MEMS accelerometer wide range modeling using artificial neural network
A. Baharodimehr; A. Abolfazl Suratgar; H. Sadeghi
2009-01-01
This paper presents a nonlinear model for a capacitive microelectromechanical accelerometer (MEMA). System parameters ofthe accelerometer are developed using the effect of cubic term of the folded‐flexure spring. To solve this equation, we use theFEA method. The neural network (NN) uses the Levenberg‐Marquardt (LM) method for training the system to have a moreaccurate response. The designed NN can identify and predict the displacement of the movable mass of accelerometer. Thesimulation result...
Capacitive MEMS accelerometer wide range modeling using artificial neural network
Directory of Open Access Journals (Sweden)
A. Baharodimehr
2009-08-01
Full Text Available This paper presents a nonlinear model for a capacitive microelectromechanical accelerometer (MEMA. System parameters ofthe accelerometer are developed using the effect of cubic term of the folded‐flexure spring. To solve this equation, we use theFEA method. The neural network (NN uses the Levenberg‐Marquardt (LM method for training the system to have a moreaccurate response. The designed NN can identify and predict the displacement of the movable mass of accelerometer. Thesimulation results are very promising.
Analysis of Natural Gradient Descent for Multilayer Neural Networks
Rattray, Magnus; Saad, David
1999-01-01
Natural gradient descent is a principled method for adapting the parameters of a statistical model on-line using an underlying Riemannian parameter space to redefine the direction of steepest descent. The algorithm is examined via methods of statistical physics which accurately characterize both transient and asymptotic behavior. A solution of the learning dynamics is obtained for the case of multilayer neural network training in the limit of large input dimension. We find that natural gradie...
Backpropagation Neural Network Implementation for Medical Image Compression
Kamil Dimililer
2013-01-01
Medical images require compression, before transmission or storage, due to constrained bandwidth and storage capacity. An ideal image compression system must yield high-quality compressed image with high compression ratio. In this paper, Haar wavelet transform and discrete cosine transform are considered and a neural network is trained to relate the X-ray image contents to their ideal compression method and their optimum compression ratio.
Backpropagation Neural Network Implementation for Medical Image Compression
Directory of Open Access Journals (Sweden)
Kamil Dimililer
2013-01-01
Full Text Available Medical images require compression, before transmission or storage, due to constrained bandwidth and storage capacity. An ideal image compression system must yield high-quality compressed image with high compression ratio. In this paper, Haar wavelet transform and discrete cosine transform are considered and a neural network is trained to relate the X-ray image contents to their ideal compression method and their optimum compression ratio.
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.
Practical application of artificial neural networks in the neurosciences
Pinti, Antonio
1995-04-01
This article presents a practical application of artificial multi-layer perceptron (MLP) neural networks in neurosciences. The data that are processed are labeled data from the visual analysis of electrical signals of human sleep. The objective of this work is to automatically classify into sleep stages the electrophysiological signals recorded from electrodes placed on a sleeping patient. Two large data bases were designed by experts in order to realize this study. One data base was used to train the network and the other to test its generalization capacity. The classification results obtained with the MLP network were compared to a type K nearest neighbor Knn non-parametric classification method. The MLP network gave a better result in terms of classification than the Knn method. Both classification techniques were implemented on a transputer system. With both networks in their final configuration, the MLP network was 160 times faster than the Knn model in classifying a sleep period.
Neural networks for prediction and control of chaotic fluidized bed hydrodynamics : A first step
Bakker, R; De Korte, RJ; Schouten, JC; Van den Bleek, CM; Takens, F
A neural-network-based model that has learnt the chaotic hydrodynamics of a fluidized bed reactor is presented. The network is trained on measured electrical capacitance tomography data. A training algorithm is used that does not only minimize the short-term prediction error but also the information
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
The relevance of network micro-structure for neural dynamics
Directory of Open Access Journals (Sweden)
Volker ePernice
2013-06-01
Full Text Available The activity of cortical neurons is determined by the input they receive from presynaptic neurons. Many previousstudies have investigated how specific aspects of the statistics of the input affect the spike trains of single neurons and neuronsin recurrent networks. However, typically very simple random network models are considered in such studies. Here weuse a recently developed algorithm to construct networks based on a quasi-fractal probability measure which are much morevariable than commonly used network models, and which therefore promise to sample the space of recurrent networks ina more exhaustive fashion than previously possible. We use the generated graphs as the underlying network topology insimulations of networks of integrate-and-fire neurons in an asynchronous and irregular state. Based on an extensive datasetof networks and neuronal simulations we assess statistical relations between features of the network structure and the spikingactivity. Our results highlight the strong influence that some details of the network structure have on the activity dynamics ofboth single neurons and populations, even if some global network parameters are kept fixed. We observe specific and consistentrelations between activity characteristics like spike-train irregularity or correlations and network properties, for example thedistributions of the numbers of in- and outgoing connections or clustering. Exploiting these relations, we demonstrate that itis possible to estimate structural characteristics of the network from activity data. We also assess higher order correlationsof spiking activity in the various networks considered here, and find that their occurrence strongly depends on the networkstructure. These results provide directions for further theoretical studies on recurrent networks, as well as new ways to interpretspike train recordings from neural circuits.
Neural network approaches for noisy language modeling.
Li, Jun; Ouazzane, Karim; Kazemian, Hassan B; Afzal, Muhammad Sajid
2013-11-01
Text entry from people is not only grammatical and distinct, but also noisy. For example, a user's typing stream contains all the information about the user's interaction with computer using a QWERTY keyboard, which may include the user's typing mistakes as well as specific vocabulary, typing habit, and typing performance. In particular, these features are obvious in disabled users' typing streams. This paper proposes a new concept called noisy language modeling by further developing information theory and applies neural networks to one of its specific application-typing stream. This paper experimentally uses a neural network approach to analyze the disabled users' typing streams both in general and specific ways to identify their typing behaviors and subsequently, to make typing predictions and typing corrections. In this paper, a focused time-delay neural network (FTDNN) language model, a time gap model, a prediction model based on time gap, and a probabilistic neural network model (PNN) are developed. A 38% first hitting rate (HR) and a 53% first three HR in symbol prediction are obtained based on the analysis of a user's typing history through the FTDNN language modeling, while the modeling results using the time gap prediction model and the PNN model demonstrate that the correction rates lie predominantly in between 65% and 90% with the current testing samples, and 70% of all test scores above basic correction rates, respectively. The modeling process demonstrates that a neural network is a suitable and robust language modeling tool to analyze the noisy language stream. The research also paves the way for practical application development in areas such as informational analysis, text prediction, and error correction by providing a theoretical basis of neural network approaches for noisy language modeling.
Transforming Musical Signals through a Genre Classifying Convolutional Neural Network
Geng, S.; Ren, G.; Ogihara, M.
2017-05-01
Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the abstracting process. One can hope to manipulate existing music based on this 'informed' network and create music with new features corresponding to the knowledge obtained by the network. In this paper, we propose a method to utilize the stored information from a CNN trained on musical genre classification task. The network was composed of three convolutional layers, and was trained to classify five-second song clips into five different genres. After training, randomly selected clips were modified by maximizing the sum of outputs from the network layers. In addition to the potential of such CNNs to produce interesting audio transformation, more information about the network and the original music could be obtained from the analysis of the generated features since these features indicate how the network 'understands' the music.
Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics
Lenhardt, L.; Zeković, I.; Dramićanin, T.; Dramićanin, M. D.
2013-11-01
Over the years various optical spectroscopic techniques have been widely used as diagnostic tools in the discrimination of many types of malignant diseases. Recently, synchronous fluorescent spectroscopy (SFS) coupled with chemometrics has been applied in cancer diagnostics. The SFS method involves simultaneous scanning of both emission and excitation wavelengths while keeping the interval of wavelengths (constant-wavelength mode) or frequencies (constant-energy mode) between them constant. This method is fast, relatively inexpensive, sensitive and non-invasive. Total synchronous fluorescence spectra of normal skin, nevus and melanoma samples were used as input for training of artificial neural networks. Two different types of artificial neural networks were trained, the self-organizing map and the feed-forward neural network. Histopathology results of investigated skin samples were used as the gold standard for network output. Based on the obtained classification success rate of neural networks, we concluded that both networks provided high sensitivity with classification errors between 2 and 4%.
Neural network connectivity and response latency modelled by stochastic processes
DEFF Research Database (Denmark)
Tamborrino, Massimiliano
is connected to thousands of other neurons. The rst question is: how to model neural networks through stochastic processes? A multivariate Ornstein-Uhlenbeck process, obtained as a diffusion approximation of a jump process, is the proposed answer. Obviously, dependencies between neurons imply dependencies...... between their spike times. Therefore, the second question is: how to detect neural network connectivity from simultaneously recorded spike trains? Answering this question corresponds to investigate the joint distribution of sequences of rst passage times. A non-parametric method based on copulas...... generation of pikes. When a stimulus is applied to the network, the spontaneous rings may prevail and hamper detection of the effects of the stimulus. Therefore, the spontaneous rings cannot be ignored and the response latency has to be detected on top of a background signal. Everything becomes more dicult...
Predicting the survival of diabetes using neural network
Mamuda, Mamman; Sathasivam, Saratha
2017-08-01
Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction
An Artificial Neural Network for Data Forecasting Purposes
Directory of Open Access Journals (Sweden)
Catalina Lucia COCIANU
2015-01-01
Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.
Human Face Identification using KL Transform and Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Kim, Yong Joo [LG Electronics Inc. Multimedia Research Lab. (Korea, Republic of); Ji, Seung Hwan [Mi Re Industry Inc. (Korea, Republic of); Yoo, Jae Hyung; Kim, Jung Hwan; Park, Min Yong [Yonsei University (Korea, Republic of)
1999-01-01
Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn`t often considered in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments. (author). 12 refs., 7 figs., 3 tabs.
Artificial neural network in cosmic landscape
Liu, Junyu
2017-12-01
In this paper we propose that artificial neural network, the basis of machine learning, is useful to generate the inflationary landscape from a cosmological point of view. Traditional numerical simulations of a global cosmic landscape typically need an exponential complexity when the number of fields is large. However, a basic application of artificial neural network could solve the problem based on the universal approximation theorem of the multilayer perceptron. A toy model in inflation with multiple light fields is investigated numerically as an example of such an application.
Automatic identification of species with neural networks.
Hernández-Serna, Andrés; Jiménez-Segura, Luz Fernanda
2014-01-01
A new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the images. Artificial neural networks (ANNs) were used as the pattern recognition method. We tested a data set that included 740 species and 11,198 individuals. Our results show that the system performed with high accuracy, reaching 91.65% of true positive fish identifications, 92.87% of plants and 93.25% of butterflies. Our results highlight how the neural networks are complementary to species identification.
Automatic identification of species with neural networks
Directory of Open Access Journals (Sweden)
Andrés Hernández-Serna
2014-11-01
Full Text Available A new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the images. Artificial neural networks (ANNs were used as the pattern recognition method. We tested a data set that included 740 species and 11,198 individuals. Our results show that the system performed with high accuracy, reaching 91.65% of true positive fish identifications, 92.87% of plants and 93.25% of butterflies. Our results highlight how the neural networks are complementary to species identification.
Pulse image recognition using fuzzy neural network.
Xu, L S; Meng, Max Q -H; Wang, K Q
2007-01-01
The automatic recognition of pulse images is the key in the research of computerized pulse diagnosis. In order to automatically differentiate the pulse patterns by using small samples, a fuzzy neural network to classify pulse images based on the knowledge of experts in traditional Chinese pulse diagnosis was designed. The designed classifier can make hard decision and soft decision for identifying 18 patterns of pulse images at the accuracy of 91%, which is better than the results that achieved by back-propagation neural network.
Assessing Landslide Hazard Using Artificial Neural Network
DEFF Research Database (Denmark)
Farrokhzad, Farzad; Choobbasti, Asskar Janalizadeh; Barari, Amin
2011-01-01
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...... 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...
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.
Short-Term Load Forecasting Model Based on Quantum Elman Neural Networks
Directory of Open Access Journals (Sweden)
Zhisheng Zhang
2016-01-01
Full Text Available Short-term load forecasting model based on quantum Elman neural networks was constructed in this paper. The quantum computation and Elman feedback mechanism were integrated into quantum Elman neural networks. Quantum computation can effectively improve the approximation capability and the information processing ability of the neural networks. Quantum Elman neural networks have not only the feedforward connection but also the feedback connection. The feedback connection between the hidden nodes and the context nodes belongs to the state feedback in the internal system, which has formed specific dynamic memory performance. Phase space reconstruction theory is the theoretical basis of constructing the forecasting model. The training samples are formed by means of K-nearest neighbor approach. Through the example simulation, the testing results show that the model based on quantum Elman neural networks is better than the model based on the quantum feedforward neural network, the model based on the conventional Elman neural network, and the model based on the conventional feedforward neural network. So the proposed model can effectively improve the prediction accuracy. The research in the paper makes a theoretical foundation for the practical engineering application of the short-term load forecasting model based on quantum Elman neural networks.
Wavelet neural networks with applications in financial engineering, chaos, and classification
Alexandridis, Antonios K
2014-01-01
Through extensive examples and case studies, Wavelet Neural Networks provides a step-by-step introduction to modeling, training, and forecasting using wavelet networks. The acclaimed authors present a statistical model identification framework to successfully apply wavelet networks in various applications, specifically, providing the mathematical and statistical framework needed for model selection, variable selection, wavelet network construction, initialization, training, forecasting and prediction, confidence intervals, prediction intervals, and model adequacy testing. The text is ideal for
Control of a hybrid compensator in a power network by an artificial neural network
Directory of Open Access Journals (Sweden)
I. S. Shaw
1998-07-01
Full Text Available Increased interest in the elimination of distortion in electrical power networks has led to the development of various compensator topologies. The increasing cost of electrical energy necessitates the cost-effective operation of any of these topologies. This paper considers the development of an artificial neural network based controller, trained by means of the backpropagation method, that ensures the cost-effective operation of the hybrid compensator consisting of various converters and filters.
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.
Effective learning in recurrent max-min neural networks.
Loe, Kia Fock; Teow, Loo Nin
1998-04-01
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly differentiable, we propose a mathematically sound learning method based on using Fourier convergence analysis of side-derivatives to derive a gradient descent technique for max-min error functions. We then propose a novel recurrent max-min neural network model that is trained to perform grammatical inference as an application example. Comparisons made between this model and recurrent sigmoidal neural networks show that our model not only performs better in terms of learning speed and generalization, but that its final weight configuration allows a deterministic finite automation (DFA) to be extracted in a straightforward manner. In essence, we are able to demonstrate that our proposed gradient descent technique does allow max-min neural networks to learn effectively.
Proceedings of the Neural Network Workshop for the Hanford Community
Energy Technology Data Exchange (ETDEWEB)
Keller, P.E.
1994-01-01
These proceedings were generated from a series of presentations made at the Neural Network Workshop for the Hanford Community. The abstracts and viewgraphs of each presentation are reproduced in these proceedings. This workshop was sponsored by the Computing and Information Sciences Department in the Molecular Science Research Center (MSRC) at the Pacific Northwest Laboratory (PNL). Artificial neural networks constitute a new information processing technology that is destined within the next few years, to provide the world with a vast array of new products. A major reason for this is that artificial neural networks are able to provide solutions to a wide variety of complex problems in a much simpler fashion than is possible using existing techniques. In recognition of these capabilities, many scientists and engineers are exploring the potential application of this new technology to their fields of study. An artificial neural network (ANN) can be a software simulation, an electronic circuit, optical system, or even an electro-chemical system designed to emulate some of the brain`s rudimentary structure as well as some of the learning processes that are believed to take place in the brain. For a very wide range of applications in science, engineering, and information technology, ANNs offer a complementary and potentially superior approach to that provided by conventional computing and conventional artificial intelligence. This is because, unlike conventional computers, which have to be programmed, ANNs essentially learn from experience and can be trained in a straightforward fashion to carry out tasks ranging from the simple to the highly complex.
Modelling and Prediction of Photovoltaic Power Output Using Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Aminmohammad Saberian
2014-01-01
Full Text Available This paper presents a solar power modelling method using artificial neural networks (ANNs. Two neural network structures, namely, general regression neural network (GRNN feedforward back propagation (FFBP, have been used to model a photovoltaic panel output power and approximate the generated power. Both neural networks have four inputs and one output. The inputs are maximum temperature, minimum temperature, mean temperature, and irradiance; the output is the power. The data used in this paper started from January 1, 2006, until December 31, 2010. The five years of data were split into two parts: 2006–2008 and 2009-2010; the first part was used for training and the second part was used for testing the neural networks. A mathematical equation is used to estimate the generated power. At the end, both of these networks have shown good modelling performance; however, FFBP has shown a better performance comparing with GRNN.
Neural Networks for Muscle Forces Prediction in Cycling
Directory of Open Access Journals (Sweden)
Giulio Cecchini
2014-11-01
Full Text Available This paper documents the research towards the development of a system based on Artificial Neural Networks to predict muscle force patterns of an athlete during cycling. Two independent inverse problems must be solved for the force estimation: evaluation of the kinematic model and evaluation of the forces distribution along the limb. By solving repeatedly the two inverse problems for different subjects and conditions, a training pattern for an Artificial Neural Network was created. Then, the trained network was validated against an independent validation set, and compared to evaluate agreement between the two alternative approaches using Bland-Altman method. The obtained neural network for the different test patterns yields a normalized error well below 1% and the Bland-Altman plot shows a considerable correlation between the two methods. The new approach proposed herein allows a direct and fast computation for the inverse dynamics of a cyclist, opening the possibility of integrating such algorithm in a real time environment such as an embedded application.
Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words
Qaralleh, Esam
2013-10-01
Artificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%.
VoIP attacks detection engine based on neural network
Safarik, Jakub; Slachta, Jiri
2015-05-01
The security is crucial for any system nowadays, especially communications. One of the most successful protocols in the field of communication over IP networks is Session Initiation Protocol. It is an open-source project used by different kinds of applications, both open-source and proprietary. High penetration and text-based principle made SIP number one target in IP telephony infrastructure, so security of SIP server is essential. To keep up with hackers and to detect potential malicious attacks, security administrator needs to monitor and evaluate SIP traffic in the network. But monitoring and following evaluation could easily overwhelm the security administrator in networks, typically in networks with a number of SIP servers, users and logically or geographically separated networks. The proposed solution lies in automatic attack detection systems. The article covers detection of VoIP attacks through a distributed network of nodes. Then the gathered data analyze aggregation server with artificial neural network. Artificial neural network means multilayer perceptron network trained with a set of collected attacks. Attack data could also be preprocessed and verified with a self-organizing map. The source data is detected by distributed network of detection nodes. Each node contains a honeypot application and traffic monitoring mechanism. Aggregation of data from each node creates an input for neural networks. The automatic classification on a centralized server with low false positive detection reduce the cost of attack detection resources. The detection system uses modular design for easy deployment in final infrastructure. The centralized server collects and process detected traffic. It also maintains all detection nodes.
Artificial Neural Network System for Thyroid Diagnosis
Directory of Open Access Journals (Sweden)
Mazin Abdulrasool Hameed
2017-05-01
Full Text Available Thyroid disease is one of major causes of severe medical problems for human beings. Therefore, proper diagnosis of thyroid disease is considered as an important issue to determine treatment for patients. This paper focuses on using Artificial Neural Network (ANN as a significant technique of artificial intelligence to diagnose thyroid diseases. The continuous values of three laboratory blood tests are used as input signals to the proposed system of ANN. All types of thyroid diseases that may occur in patients are taken into account in design of system, as well as the high accuracy of the detection and categorization of thyroid diseases are considered in the system. A multilayer feedforward architecture of ANN is adopted in the proposed design, and the back propagation is selected as learning algorithm to accomplish the training process. The result of this research shows that the proposed ANN system is able to precisely diagnose thyroid disease, and can be exploited in practical uses. The system is simulated via MATLAB software to evaluate its performance
MHC haplotype analysis by artificial neural networks.
Bellgard, M I; Tay, G K; Hiew, H L; Witt, C S; Ketheesan, N; Christiansen, F T; Dawkins, R L
1998-01-01
Conventional matching is based on numbers of alleles shared between donor and recipient. This approach, however, ignores the degree of relationship between alleles and haplotypes, and therefore the actual degree of difference. To address this problem, we have compared family members using a block matching technique which reflects differences in genomic sequences. All parents and siblings had been genotyped using conventional MHC typing so that haplotypes could be assigned and relatives could be classified as sharing 0, 1 or 2 haplotypes. We trained an Artificial Neural Network (ANN) with subjects from 6 families (85 comparisons) to distinguish between relatives. Using the outputs of the ANN, we developed a score, the Histocompatibility Index (HI), as a measure of the degree of difference. Subjects from a further 3 families (106 profile comparisons) were tested. The HI score for each comparison was plotted. We show that the HI score is trimodal allowing the definition of three populations corresponding to approximately 0, 1 or 2 haplotype sharing. The means and standard deviations of the three populations were found. As expected, comparisons between family members sharing 2 haplotypes resulted in high HI scores with one exception. More interestingly, this approach distinguishes between the 1 and 0 haplotype groups, with some informative exceptions. This distinction was considered too difficult to attempt visually. The approach provides promise in the quantification of degrees of histocompatibility.
Removing Epistemological Bias From Empirical Observation of Neural Networks
Waldron, Ronan
1994-01-01
Also in Proceedings of the International Joint Conference on Neural Networks, Nagoya, Japan. This paper addresses the application of neural network research to a theory of autonomous systems. Neural networks, while enjoying considerable success in autonomous systems applications, have failed to provide a firm theoretical underpinning to neural systems embedded in their natural ecological context. This paper proposes a stochastic formulation of such an embedding. A neural sys...
Using Neural Networks to Determine the Origin of Medical Ultrasound Images
Fossan, Øivind
2017-01-01
This thesis investigates the possibility of using neural networks to determine the body location of medical ultrasound images. Neural networks were trained on several datasets of both synthetic and real ultrasound images, containing labels with the location of each image. Next, the networks predicted the location of unseen images, and the accuracy was measured. The first dataset consisted of images from three typical locations for ultrasound-guided regional anesthesia, where a classificat...
Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures
DEFF Research Database (Denmark)
Christiansen, Niels H.; Voie, Per Erlend Torbergsen; Winther, Ole
2014-01-01
platform is designed and tested. The purpose of setting up the network is to reduce calculation time in a fatigue life analysis. Therefore, the networks trained on different error functions are compared with respect to accuracy of rain flow counts of stress cycles over a number of time series simulations......Training of an artificial neural network (ANN) adjusts the internal weights of the network in order to minimize a predefined error measure. This error measure is given by an error function. Several different error functions are suggested in the literature. However, the far most common measure...... for regression is the mean square error. This paper looks into the possibility of improving the performance of neural networks by selecting or defining error functions that are tailor-made for a specific objective. A neural network trained to simulate tension forces in an anchor chain on a floating offshore...
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....
On The Comparison of Artificial Neural Network (ANN) and ...
African Journals Online (AJOL)
West African Journal of Industrial and Academic Research ... This work presented the results of an experimental comparison of two models: Multinomial Logistic Regression (MLR) and Artificial Neural Network (ANN) for ... Keywords: Multinomial Logistic Regression, Artificial Neural Network, Correct classification rate.
A NEURAL OSCILLATOR-NETWORK MODEL OF TEMPORAL PATTERN GENERATION
Schomaker, Lambert
Most contemporary neural network models deal with essentially static, perceptual problems of classification and transformation. Models such as multi-layer feedforward perceptrons generally do not incorporate time as an essential dimension, whereas biological neural networks are inherently temporal
Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks
Ray, Loye Lynn
2014-01-01
The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…
A mixed-scale dense convolutional neural network for image analysis
D.M. Pelt (Daniel); J.A. Sethian (James)
2016-01-01
textabstractDeep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results
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.
Precipitation Estimation from Remotely Sensed Data Using Deep Neural Network
Tao, Y.; Gao, X.; Hsu, K. L.; Sorooshian, S.; Ihler, A.
2015-12-01
This research develops a precipitation estimation system from remote sensed data using state-of-the-art machine learning algorithms. Compared to ground-based precipitation measurements, satellite-based precipitation estimation products have advantages of temporal resolution and spatial coverage. Also, the massive amount of satellite data contains various measures related to precipitation formation and development. On the other hand, deep learning algorithms were newly developed in the area of machine learning, which was a breakthrough to deal with large and complex dataset, especially to image data. Here, we attempt to engage deep learning techniques to provide hourly precipitation estimation from satellite information, such as long wave infrared data. The brightness temperature data from infrared data is considered to contain cloud information. Radar stage IV dataset is used as ground measurement for parameter calibration. Stacked denoising auto-encoders (SDAE) is applied here to build a 4-layer neural network with 1000 hidden nodes for each hidden layer. SDAE involves two major steps: (1) greedily pre-training each layer as a denoising auto-encoder using the outputs of previous trained hidden layer output starting from visible layer to initialize parameters; (2) fine-tuning the whole deep neural network with supervised criteria. The results are compared with satellite precipitation product PERSIANN-CCS (Precipitation Estimation from Remotely Sensed Imagery using an Artificial Neural Network Cloud Classification System). Based on the results, we have several valuable conclusions: By properly training the neural network, it is able to extract useful information for precipitation estimation. For example, it can reduce the mean squared error of the precipitation by 58% for the summer season in the central United States of the validation period. The SDAE method captures the shape of the precipitation from the cloud shape better compared to the CCS product. Design of
Yao, Kun
2015-01-01
We demonstrate a convolutional neural network trained to reproduce the Kohn-Sham kinetic energy of hydrocarbons from electron density. The output of the network is used as a non-local correction to the conventional local and semi-local kinetic functionals. We show that this approximation qualitatively reproduces Kohn-Sham potential energy surfaces when used with conventional exchange correlation functionals. Numerical noise inherited from the non-linearity of the neural network is identified as the major challenge for the model. Finally we examine the features in the density learned by the neural network to anticipate the prospects of generalizing these models.
Neural network for sonogram gap filling
DEFF Research Database (Denmark)
Klebæk, Henrik; Jensen, Jørgen Arendt; Hansen, Lars Kai
1995-01-01
a neural network for predicting mean frequency of the velocity signal and its variance. The neural network then predicts the evolution of the mean and variance in the gaps, and the sonogram and audio signal are reconstructed from these. The technique is applied on in-vivo data from the carotid artery...... 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...... series, and is shown to yield better results, i.e., the variances of the predictions are lower. The ability of the neural predictor to reconstruct both the sonogram and the audio signal, when only 50% of the time is used for velocity data acquisition, is demonstrated for the in-vivo data...
Digital Neural Networks for New Media
Spaanenburg, Lambert; Malki, Suleyman
Neural Networks perform computationally intensive tasks offering smart solutions for many new media applications. A number of analog and mixed digital/analog implementations have been proposed to smooth the algorithmic gap. But gradually, the digital implementation has become feasible, and the dedicated neural processor is on the horizon. A notable example is the Cellular Neural Network (CNN). The analog direction has matured for low-power, smart vision sensors; the digital direction is gradually being shaped into an IP-core for algorithm acceleration, especially for use in FPGA-based high-performance systems. The chapter discusses the next step towards a flexible and scalable multi-core engine using Application-Specific Integrated Processors (ASIP). This topographic engine can serve many new media tasks, as illustrated by novel applications in Homeland Security. We conclude with a view on the CNN kaleidoscope for the year 2020.