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
Dimensionality reduction in conic section function neural network
Indian Academy of Sciences (India)
This paper details how dimensionality can be reduced in conic section function neural networks (CSFNN). This is particularly important for hardware implementation of networks. One of the main problems to be solved when considering the hardware design is the high connectivity requirement. If the effect that each of the ...
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.
Radial basis function neural network in fault detection of automotive ...
African Journals Online (AJOL)
Radial basis function neural network in fault detection of automotive engines. Adnan Hamad, Dingli Yu, JB Gomm, Mahavir S Sangha. Abstract. Fault detection and isolation have become one of the most important aspects of automobile design. A fault detection (FD) scheme is developed for automotive engines in this paper.
Evaluating Functional Autocorrelation within Spatially Distributed Neural Processing Networks*
Derado, Gordana; Bowman, F. Dubois; Ely, Timothy D.; Kilts, Clinton D.
2010-01-01
Data-driven statistical approaches, such as cluster analysis or independent component analysis, applied to in vivo functional neuroimaging data help to identify neural processing networks that exhibit similar task-related or restingstate patterns of activity. Ideally, the measured brain activity for voxels within such networks should exhibit high autocorrelation. An important limitation is that the algorithms do not typically quantify or statistically test the strength or nature of the within-network relatedness between voxels. To extend the results given by such data-driven analyses, we propose the use of Moran’s I statistic to measure the degree of functional autocorrelation within identified neural processing networks and to evaluate the statistical significance of the observed associations. We adapt the conventional definition of Moran’s I, for applicability to neuroimaging analyses, by defining the global autocorrelation index using network-based neighborhoods. Also, we compute network-specific contributions to the overall autocorrelation. We present results from a bootstrap analysis that provide empirical support for the use of our hypothesis testing framework. We illustrate our methodology using positron emission tomography (PET) data from a study that examines the neural representation of working memory among individuals with schizophrenia and functional magnetic resonance imaging (fMRI) data from a study of depression. PMID:21643436
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
Neural Networks for Approximating the Cost and Production Functions
Tsionas, Efthymios G.; Michaelides, Panayotis G.; Vouldis, Angelos
2008-01-01
Most business decisions depend on accurate approximations to the cost and production functions. Traditionally, the estimation of cost and production functions in economics relies on standard specifications which are less than satisfactory in numerous situations. However, instead of fitting the data with a pre-specified model, Artificial Neural Networks let the data itself serve as evidence to support the model’s estimation of the underlying process. In this context, the proposed approach c...
A Novel Learning Scheme for Chebyshev Functional Link Neural Networks
Directory of Open Access Journals (Sweden)
Satchidananda Dehuri
2011-01-01
dimensional-space where linear separability is possible. Moreover, the proposed HCFLNN combines the best attribute of particle swarm optimization (PSO, back propagation learning (BP learning, and functional link neural networks (FLNNs. The proposed method eliminates the need of hidden layer by expanding the input patterns using Chebyshev orthogonal polynomials. We have shown its effectiveness of classifying the unknown pattern using the publicly available datasets obtained from UCI repository. The computational results are then compared with functional link neural network (FLNN with a generic basis functions, PSO-based FLNN, and EFLN. From the comparative study, we observed that the performance of the HCFLNN outperforms FLNN, PSO-based FLNN, and EFLN in terms of classification accuracy.
Using neural networks to predict the functionality of reconfigurable nano-material networks
Greff, Klaus; van Damme, Rudolf M.J.; Koutnik, Jan; Broersma, Haitze J.; Mikhal, Julia Olegivna; Lawrence, Celestine Preetham; van der Wiel, Wilfred Gerard; Schmidhuber, Jürgen
2017-01-01
This paper demonstrates how neural networks can be applied to model and predict the functional behaviour of disordered nano-particle and nano-tube networks. In recently published experimental work, nano-particle and nano-tube networks show promising functionality for future reconfigurable devices,
Density functional and neural network analysis
DEFF Research Database (Denmark)
Jalkanen, K. J.; Suhai, S.; Bohr, Henrik
1997-01-01
Density functional theory (DFT) calculations have been carried out for hydrated L-alanine, L-alanyl-L-alanine and N-acetyl L-alanine N'-methylamide and examined with respect to the effect of water on the structure, the vibrational frequencies, vibrational absorption (VA) and vibrational circular...
Yeh, Wei-Chang
Network reliability is an important index to the provision of useful information for decision support in the modern world. There is always a need to calculate symbolic network reliability functions (SNRFs) due to dynamic and rapid changes in network parameters. In this brief, the proposed squeezed artificial neural network (SqANN) approach uses the Monte Carlo simulation to estimate the corresponding reliability of a given designed matrix from the Box-Behnken design, and then the Taguchi method is implemented to find the appropriate number of neurons and activation functions of the hidden layer and the output layer in ANN to evaluate SNRFs. According to the experimental results of the benchmark networks, the comparison appears to support the superiority of the proposed SqANN method over the traditional ANN-based approach with at least 16.6% improvement in the median absolute deviation in the cost of extra 2 s on average for all experiments.Network reliability is an important index to the provision of useful information for decision support in the modern world. There is always a need to calculate symbolic network reliability functions (SNRFs) due to dynamic and rapid changes in network parameters. In this brief, the proposed squeezed artificial neural network (SqANN) approach uses the Monte Carlo simulation to estimate the corresponding reliability of a given designed matrix from the Box-Behnken design, and then the Taguchi method is implemented to find the appropriate number of neurons and activation functions of the hidden layer and the output layer in ANN to evaluate SNRFs. According to the experimental results of the benchmark networks, the comparison appears to support the superiority of the proposed SqANN method over the traditional ANN-based approach with at least 16.6% improvement in the median absolute deviation in the cost of extra 2 s on average for all experiments.
Vuković, Najdan; Miljković, Zoran
2013-10-01
Radial basis function (RBF) neural network is constructed of certain number of RBF neurons, and these networks are among the most used neural networks for modeling of various nonlinear problems in engineering. Conventional RBF neuron is usually based on Gaussian type of activation function with single width for each activation function. This feature restricts neuron performance for modeling the complex nonlinear problems. To accommodate limitation of a single scale, this paper presents neural network with similar but yet different activation function-hyper basis function (HBF). The HBF allows different scaling of input dimensions to provide better generalization property when dealing with complex nonlinear problems in engineering practice. The HBF is based on generalization of Gaussian type of neuron that applies Mahalanobis-like distance as a distance metrics between input training sample and prototype vector. Compared to the RBF, the HBF neuron has more parameters to optimize, but HBF neural network needs less number of HBF neurons to memorize relationship between input and output sets in order to achieve good generalization property. However, recent research results of HBF neural network performance have shown that optimal way of constructing this type of neural network is needed; this paper addresses this issue and modifies sequential learning algorithm for HBF neural network that exploits the concept of neuron's significance and allows growing and pruning of HBF neuron during learning process. Extensive experimental study shows that HBF neural network, trained with developed learning algorithm, achieves lower prediction error and more compact neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.
Neuronal spike sorting based on radial basis function neural networks
Directory of Open Access Journals (Sweden)
Taghavi Kani M
2011-02-01
Full Text Available "nBackground: Studying the behavior of a society of neurons, extracting the communication mechanisms of brain with other tissues, finding treatment for some nervous system diseases and designing neuroprosthetic devices, require an algorithm to sort neuralspikes automatically. However, sorting neural spikes is a challenging task because of the low signal to noise ratio (SNR of the spikes. The main purpose of this study was to design an automatic algorithm for classifying neuronal spikes that are emitted from a specific region of the nervous system."n "nMethods: The spike sorting process usually consists of three stages: detection, feature extraction and sorting. We initially used signal statistics to detect neural spikes. Then, we chose a limited number of typical spikes as features and finally used them to train a radial basis function (RBF neural network to sort the spikes. In most spike sorting devices, these signals are not linearly discriminative. In order to solve this problem, the aforesaid RBF neural network was used."n "nResults: After the learning process, our proposed algorithm classified any arbitrary spike. The obtained results showed that even though the proposed Radial Basis Spike Sorter (RBSS reached to the same error as the previous methods, however, the computational costs were much lower compared to other algorithms. Moreover, the competitive points of the proposed algorithm were its good speed and low computational complexity."n "nConclusion: Regarding the results of this study, the proposed algorithm seems to serve the purpose of procedures that require real-time processing and spike sorting.
Nuclear charge radii: density functional theory meets Bayesian neural networks
Utama, R.; Chen, Wei-Chia; Piekarewicz, J.
2016-11-01
The distribution of electric charge in atomic nuclei is fundamental to our understanding of the complex nuclear dynamics and a quintessential observable to validate nuclear structure models. The aim of this study is to explore a novel approach that combines sophisticated models of nuclear structure with Bayesian neural networks (BNN) to generate predictions for the charge radii of thousands of nuclei throughout the nuclear chart. A class of relativistic energy density functionals is used to provide robust predictions for nuclear charge radii. In turn, these predictions are refined through Bayesian learning for a neural network that is trained using residuals between theoretical predictions and the experimental data. Although predictions obtained with density functional theory provide a fairly good description of experiment, our results show significant improvement (better than 40%) after BNN refinement. Moreover, these improved results for nuclear charge radii are supplemented with theoretical error bars. We have successfully demonstrated the ability of the BNN approach to significantly increase the accuracy of nuclear models in the predictions of nuclear charge radii. However, as many before us, we failed to uncover the underlying physics behind the intriguing behavior of charge radii along the calcium isotopic chain.
Zhang, Songchuan; Xia, Youshen; Wang, Jun
2015-12-01
In this paper, we present a complex-valued projection neural network for solving constrained convex optimization problems of real functions with complex variables, as an extension of real-valued projection neural networks. Theoretically, by developing results on complex-valued optimization techniques, we prove that the complex-valued projection neural network is globally stable and convergent to the optimal solution. Obtained results are completely established in the complex domain and thus significantly generalize existing results of the real-valued projection neural networks. Numerical simulations are presented to confirm the obtained results and effectiveness of the proposed complex-valued projection neural network.
Cheng, Longlong; Zhang, Guangju; Wan, Baikun; Hao, Linlin; Qi, Hongzhi; Ming, Dong
2009-01-01
Functional electrical stimulation (FES) has been widely used in the area of neural engineering. It utilizes electrical current to activate nerves innervating extremities affected by paralysis. An effective combination of a traditional PID controller and a neural network, being capable of nonlinear expression and adaptive learning property, supply a more reliable approach to construct FES controller that help the paraplegia complete the action they want. A FES system tuned by Radial Basis Function (RBF) Neural Network-based Proportional-Integral-Derivative (PID) model was designed to control the knee joint according to the desired trajectory through stimulation of lower limbs muscles in this paper. Experiment result shows that the FES system with RBF Neural Network-based PID model get a better performance when tracking the preset trajectory of knee angle comparing with the system adjusted by Ziegler- Nichols tuning PID model.
Dimensionality reduction in conic section function neural network
Indian Academy of Sciences (India)
R. Narasimhan (Krishtel eMaging) 1461 1996 Oct 15 13:05:22
layer, for input pattern p and θj is the threshold value. The output of the hidden ... The weights, centres and angle values are updated using error back propagation so that the network would converge ..... Delgado-Frias J G, Moore W R 1994 VLSI for neural networks and artificial intelligence (New York: Plenum). Dorffner G ...
Neural Network Hydrological Modelling: Linear Output Activation Functions?
Abrahart, R. J.; Dawson, C. W.
2005-12-01
The power to represent non-linear hydrological processes is of paramount importance in neural network hydrological modelling operations. The accepted wisdom requires non-polynomial activation functions to be incorporated in the hidden units such that a single tier of hidden units can thereafter be used to provide a 'universal approximation' to whatever particular hydrological mechanism or function is of interest to the modeller. The user can select from a set of default activation functions, or in certain software packages, is able to define their own function - the most popular options being logistic, sigmoid and hyperbolic tangent. If a unit does not transform its inputs it is said to possess a 'linear activation function' and a combination of linear activation functions will produce a linear solution; whereas the use of non-linear activation functions will produce non-linear solutions in which the principle of superposition does not hold. For hidden units, speed of learning and network complexities are important issues. For the output units, it is desirable to select an activation function that is suited to the distribution of the target values: e.g. binary targets (logistic); categorical targets (softmax); continuous-valued targets with a bounded range (logistic / tanh); positive target values with no known upper bound (exponential; but beware of overflow); continuous-valued targets with no known bounds (linear). It is also standard practice in most hydrological applications to use the default software settings and to insert a set of identical non-linear activation functions in the hidden layer and output layer processing units. Mixed combinations have nevertheless been reported in several hydrological modelling papers and the full ramifications of such activities requires further investigation and assessment i.e. non-linear activation functions in the hidden units connected to linear or clipped-linear activation functions in the output unit. There are two
Liu, Jinkun
2013-01-01
Radial Basis Function (RBF) Neural Network Control for Mechanical Systems is motivated by the need for systematic design approaches to stable adaptive control system design using neural network approximation-based techniques. The main objectives of the book are to introduce the concrete design methods and MATLAB simulation of stable adaptive RBF neural control strategies. In this book, a broad range of implementable neural network control design methods for mechanical systems are presented, such as robot manipulators, inverted pendulums, single link flexible joint robots, motors, etc. Advanced neural network controller design methods and their stability analysis are explored. The book provides readers with the fundamentals of neural network control system design. This book is intended for the researchers in the fields of neural adaptive control, mechanical systems, Matlab simulation, engineering design, robotics and automation. Jinkun Liu is a professor at Beijing University of Aeronautics and Astronauti...
Models of Hopfield-type quaternion neural networks and their energy functions.
Yoshida, Mitsuo; Kuroe, Yasuaki; Mori, Takehiro
2005-01-01
Recently models of neural networks that can directly deal with complex numbers, complex-valued neural networks, have been proposed and several studies on their abilities of information processing have been done. Furthermore models of neural networks that can deal with quaternion numbers, which is the extension of complex numbers, have also been proposed. However they are all multilayer quaternion neural networks. This paper proposes models of fully connected recurrent quaternion neural networks, Hopfield-type quaternion neural networks. Since quaternion numbers are non-commutative on multiplication, some different models can be considered. We investigate dynamics of these proposed models from the point of view of the existence of an energy function and derive their conditions for existence.
Directory of Open Access Journals (Sweden)
WenJun Zhang
2014-06-01
Full Text Available In present study we used self-organizing map (SOM neural network to conduct the non-supervisory clustering of invertebrate orders in rice field. Four topological functions, i.e., cossintopf, sincostopf, acossintopf, and expsintopf, established on the template in toolbox of Matlab, were used in SOM neural network learning. Results showed that clusters were different when using different topological functions because different topological functions will generate different spatial structure of neurons in neural network. We may chose these functions and results based on comparison with the practical situation.
High-Dimensional Function Approximation With Neural Networks for Large Volumes of Data.
Andras, Peter
2018-02-01
Approximation of high-dimensional functions is a challenge for neural networks due to the curse of dimensionality. Often the data for which the approximated function is defined resides on a low-dimensional manifold and in principle the approximation of the function over this manifold should improve the approximation performance. It has been show that projecting the data manifold into a lower dimensional space, followed by the neural network approximation of the function over this space, provides a more precise approximation of the function than the approximation of the function with neural networks in the original data space. However, if the data volume is very large, the projection into the low-dimensional space has to be based on a limited sample of the data. Here, we investigate the nature of the approximation error of neural networks trained over the projection space. We show that such neural networks should have better approximation performance than neural networks trained on high-dimensional data even if the projection is based on a relatively sparse sample of the data manifold. We also find that it is preferable to use a uniformly distributed sparse sample of the data for the purpose of the generation of the low-dimensional projection. We illustrate these results considering the practical neural network approximation of a set of functions defined on high-dimensional data including real world data as well.
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.
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.
Prediction of caspase cleavage sites using Bayesian bio-basis function neural networks.
Yang, Zheng Rong
2005-05-01
Apoptosis has drawn the attention of researchers because of its importance in treating some diseases through finding a proper way to block or slow down the apoptosis process. Having understood that caspase cleavage is the key to apoptosis, we find novel methods or algorithms are essential for studying the specificity of caspase cleavage activity and this helps the effective drug design. As bio-basis function neural networks have proven to outperform some conventional neural learning algorithms, there is a motivation, in this study, to investigate the application of bio-basis function neural networks for the prediction of caspase cleavage sites. Thirteen protein sequences with experimentally determined caspase cleavage sites were downloaded from NCBI. Bayesian bio-basis function neural networks are investigated and the comparisons with single-layer perceptrons, multilayer perceptrons, the original bio-basis function neural networks and support vector machines are given. The impact of the sliding window size used to generate sub-sequences for modelling on prediction accuracy is studied. The results show that the Bayesian bio-basis function neural network with two Gaussian distributions for model parameters (weights) performed the best and the highest prediction accuracy is 97.15 +/- 1.13%. The package of Bayesian bio-basis function neural network can be obtained by request to the author.
Directory of Open Access Journals (Sweden)
Santosh Kumar Nanda
2011-01-01
Full Text Available Functional link-based neural network models were applied to predict opencast mining machineries noise. The paper analyzes the prediction capabilities of functional link neural network based noise prediction models vis-à-vis existing statistical models. In order to find the actual noise status in opencast mines, some of the popular noise prediction models, for example, ISO-9613-2, CONCAWE, VDI, and ENM, have been applied in mining and allied industries to predict the machineries noise by considering various attenuation factors. Functional link artificial neural network (FLANN, polynomial perceptron network (PPN, and Legendre neural network (LeNN were used to predict the machinery noise in opencast mines. The case study is based on data collected from an opencast coal mine of Orissa, India. From the present investigations, it could be concluded that the FLANN model give better noise prediction than the PPN and LeNN model.
Upset Prediction in Friction Welding Using Radial Basis Function Neural Network
Directory of Open Access Journals (Sweden)
Wei Liu
2013-01-01
Full Text Available This paper addresses the upset prediction problem of friction welded joints. Based on finite element simulations of inertia friction welding (IFW, a radial basis function (RBF neural network was developed initially to predict the final upset for a number of welding parameters. The predicted joint upset by the RBF neural network was compared to validated finite element simulations, producing an error of less than 8.16% which is reasonable. Furthermore, the effects of initial rotational speed and axial pressure on the upset were investigated in relation to energy conversion with the RBF neural network. The developed RBF neural network was also applied to linear friction welding (LFW and continuous drive friction welding (CDFW. The correlation coefficients of RBF prediction for LFW and CDFW were 0.963 and 0.998, respectively, which further suggest that an RBF neural network is an effective method for upset prediction of friction welded joints.
A canonical correlation neural network for multicollinearity and functional data.
Gou, Zhenkun; Fyfe, Colin
2004-03-01
We review a recent neural implementation of Canonical Correlation Analysis and show, using ideas suggested by Ridge Regression, how to make the algorithm robust. The network is shown to operate on data sets which exhibit multicollinearity. We develop a second model which not only performs as well on multicollinear data but also on general data sets. This model allows us to vary a single parameter so that the network is capable of performing Partial Least Squares regression (at one extreme) to Canonical Correlation Analysis (at the other)and every intermediate operation between the two. On multicollinear data, the parameter setting is shown to be important but on more general data no particular parameter setting is required. Finally, we develop a second penalty term which acts on such data as a smoother in that the resulting weight vectors are much smoother and more interpretable than the weights without the robustification term. We illustrate our algorithms on both artificial and real data.
Wang, Pengbo
2017-11-01
In this paper, the radial basis function (RBF) neural network is used for the mechanical fault diagnosis of a gearbox. We introduce the basic principles of the RBF neural network which is used for pattern classification and features a fast learning pace and strong nonlinear mapping capability; thus, it can be employed for fault diagnosis. The gearbox is a widely-used piece of equipment in engineering, and diagnosing mechanical faults is of great significance for engineers. A numerical example is presented to demonstrate the capability of the proposed method. The results indicate that the mechanical faults of a gearbox can be correctly diagnosed with a trained RBF neural network.
A hybrid ART-GRNN online learning neural network with a epsilon -insensitive loss function.
Yap, Keem Siah; Lim, Chee Peng; Abidin, Izham Zainal
2008-09-01
In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.
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...
Noise Reduction Technique for Images using Radial Basis Function Neural Networks
Directory of Open Access Journals (Sweden)
Sander Ali Khowaja
2014-07-01
Full Text Available This paper presents a NN (Neural Network based model for reducing the noise from images. This is a RBF (Radial Basis Function network which is used to reduce the effect of noise and blurring from the captured images. The proposed network calculates the mean MSE (Mean Square Error and PSNR (Peak Signal to Noise Ratio of the noisy images. The proposed network has also been successfully applied to medical images. The performance of the trained RBF network has been compared with the MLP (Multilayer Perceptron Network and it has been demonstrated that the performance of the RBF network is better than the MLP network.
Diagnosis of Cervical Cancer Using the Median M-Type Radial Basis Function (MMRBF) Neural Network
Gómez-Mayorga, Margarita E.; Gallegos-Funes, Francisco J.; de-La-Rosa-Vázquez, José M.; Cruz-Santiago, Rene; Ponomaryov, Volodymyr
The automatic analysis of Pap smear microscopic images is one of the most interesting fields in biomedical image processing. In this paper we present the capability of the Median M-Type Radial Basis Function (MMRBF) neural network in the classification of cervical cancer cells. From simulation results we observe that the MMRBF neural network has better classification capabilities in comparison with the Median RBF algorithm used as comparative.
Hong, Xia
2006-07-01
In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.
Modeling the Flux-Charge Relation of Memristor with Neural Network of Smooth Hinge Functions
Directory of Open Access Journals (Sweden)
X. Mu
2014-09-01
Full Text Available The memristor was proposed to characterize the flux-charge relation. We propose the generalized flux-charge relation model of memristor with neural network of smooth hinge functions. There is effective identification algorithm for the neural network of smooth hinge functions. The representation capability of this model is theoretically guaranteed. Any functional flux-charge relation of a memristor can be approximated by the model. We also give application examples to show that the given model can approximate the flux-charge relation of existing piecewise linear memristor model, window function memristor model, and a physical memristor device.
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.
Ding, Xiao Pan; Wu, Si Jia; Liu, Jiangang; Fu, Genyue; Lee, Kang
2017-09-21
The present study examined how different brain regions interact with each other during spontaneous honest vs. dishonest communication. More specifically, we took a complex network approach based on the graph-theory to analyze neural response data when children are spontaneously engaged in honest or dishonest acts. Fifty-nine right-handed children between 7 and 12 years of age participated in the study. They lied or told the truth out of their own volition. We found that lying decreased both the global and local efficiencies of children's functional neural network. This finding, for the first time, suggests that lying disrupts the efficiency of children's cortical network functioning. Further, it suggests that the graph theory based network analysis is a viable approach to study the neural development of deception.
Sengupta, Abhronil; Shim, Yong; Roy, Kaushik
2016-12-01
Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking the neuron, or the synapse functionality. While memristive devices have been proposed to emulate biological synapses, spintronic devices have proved to be efficient at performing the thresholding operation of the neuron at ultra-low currents. In this work, we propose an All-Spin Artificial Neural Network where a single spintronic device acts as the basic building block of the system. The device offers a direct mapping to synapse and neuron functionalities in the brain while inter-layer network communication is accomplished via CMOS transistors. To the best of our knowledge, this is the first demonstration of a neural architecture where a single nanoelectronic device is able to mimic both neurons and synapses. The ultra-low voltage operation of low resistance magneto-metallic neurons enables the low-voltage operation of the array of spintronic synapses, thereby leading to ultra-low power neural architectures. Device-level simulations, calibrated to experimental results, was used to drive the circuit and system level simulations of the neural network for a standard pattern recognition problem. Simulation studies indicate energy savings by ∼ 100× in comparison to a corresponding digital/analog CMOS neuron implementation.
Atom-centered symmetry functions for constructing high-dimensional neural network potentials
Behler, Jörg
2011-02-01
Neural networks offer an unbiased and numerically very accurate approach to represent high-dimensional ab initio potential-energy surfaces. Once constructed, neural network potentials can provide the energies and forces many orders of magnitude faster than electronic structure calculations, and thus enable molecular dynamics simulations of large systems. However, Cartesian coordinates are not a good choice to represent the atomic positions, and a transformation to symmetry functions is required. Using simple benchmark systems, the properties of several types of symmetry functions suitable for the construction of high-dimensional neural network potential-energy surfaces are discussed in detail. The symmetry functions are general and can be applied to all types of systems such as molecules, crystalline and amorphous solids, and liquids.
A prediction method for the wax deposition rate based on a radial basis function neural network
Directory of Open Access Journals (Sweden)
Ying Xie
2017-06-01
Full Text Available The radial basis function neural network is a popular supervised learning tool based on machinery learning technology. Its high precision having been proven, the radial basis function neural network has been applied in many areas. The accumulation of deposited materials in the pipeline may lead to the need for increased pumping power, a decreased flow rate or even to the total blockage of the line, with losses of production and capital investment, so research on predicting the wax deposition rate is significant for the safe and economical operation of an oil pipeline. This paper adopts the radial basis function neural network to predict the wax deposition rate by considering four main influencing factors, the pipe wall temperature gradient, pipe wall wax crystal solubility coefficient, pipe wall shear stress and crude oil viscosity, by the gray correlational analysis method. MATLAB software is employed to establish the RBF neural network. Compared with the previous literature, favorable consistency exists between the predicted outcomes and the experimental results, with a relative error of 1.5%. It can be concluded that the prediction method of wax deposition rate based on the RBF neural network is feasible.
Kirwan, Peter; Turner-Bridger, Benita; Peter, Manuel; Momoh, Ayiba; Arambepola, Devika; Robinson, Hugh P C; Livesey, Frederick J
2015-09-15
A key aspect of nervous system development, including that of the cerebral cortex, is the formation of higher-order neural networks. Developing neural networks undergo several phases with distinct activity patterns in vivo, which are thought to prune and fine-tune network connectivity. We report here that human pluripotent stem cell (hPSC)-derived cerebral cortex neurons form large-scale networks that reflect those found in the developing cerebral cortex in vivo. Synchronised oscillatory networks develop in a highly stereotyped pattern over several weeks in culture. An initial phase of increasing frequency of oscillations is followed by a phase of decreasing frequency, before giving rise to non-synchronous, ordered activity patterns. hPSC-derived cortical neural networks are excitatory, driven by activation of AMPA- and NMDA-type glutamate receptors, and can undergo NMDA-receptor-mediated plasticity. Investigating single neuron connectivity within PSC-derived cultures, using rabies-based trans-synaptic tracing, we found two broad classes of neuronal connectivity: most neurons have small numbers (40). These data demonstrate that the formation of hPSC-derived cortical networks mimics in vivo cortical network development and function, demonstrating the utility of in vitro systems for mechanistic studies of human forebrain neural network biology. © 2015. Published by The Company of Biologists Ltd.
Directory of Open Access Journals (Sweden)
Siebler Mario
2009-08-01
Full Text Available Abstract Background The present work was performed to investigate the ability of two different embryonic stem (ES cell-derived neural precursor populations to generate functional neuronal networks in vitro. The first ES cell-derived neural precursor population was cultivated as free-floating neural aggregates which are known to form a developmental niche comprising different types of neural cells, including neural precursor cells (NPCs, progenitor cells and even further matured cells. This niche provides by itself a variety of different growth factors and extracellular matrix proteins that influence the proliferation and differentiation of neural precursor and progenitor cells. The second population was cultivated adherently in monolayer cultures to control most stringently the extracellular environment. This population comprises highly homogeneous NPCs which are supposed to represent an attractive way to provide well-defined neuronal progeny. However, the ability of these different ES cell-derived immature neural cell populations to generate functional neuronal networks has not been assessed so far. Results While both precursor populations were shown to differentiate into sufficient quantities of mature NeuN+ neurons that also express GABA or vesicular-glutamate-transporter-2 (vGlut2, only aggregate-derived neuronal populations exhibited a synchronously oscillating network activity 24 weeks after initiating the differentiation as detected by the microelectrode array technology. Neurons derived from homogeneous NPCs within monolayer cultures did merely show uncorrelated spiking activity even when differentiated for up to 12 weeks. We demonstrated that these neurons exhibited sparsely ramified neurites and an embryonic vGlut2 distribution suggesting an inhibited terminal neuronal maturation. In comparison, neurons derived from heterogeneous populations within neural aggregates appeared as fully mature with a dense neurite network and punctuated
Directory of Open Access Journals (Sweden)
Jun Li
2009-01-01
Full Text Available The original Hopfield neural networks model is adapted so that the weights of the resulting network are time varying. In this paper, the Discrete Hopfield neural networks with weight function matrix (DHNNWFM the weight changes with time, are considered, and the stability of DHNNWFM is analyzed. Combined with the Lyapunov function, we obtain some important results that if weight function matrix (WFM is weakly (or strongly nonnegative definite function matrix, the DHNNWFM will converge to a stable state in serial (or parallel model, and if WFM consisted of strongly nonnegative definite function matrix and column (or row diagonally dominant function matrix, DHNNWFM will converge to a stable state in parallel model.
Complete stability of delayed recurrent neural networks with Gaussian activation functions.
Liu, Peng; Zeng, Zhigang; Wang, Jun
2017-01-01
This paper addresses the complete stability of delayed recurrent neural networks with Gaussian activation functions. By means of the geometrical properties of Gaussian function and algebraic properties of nonsingular M-matrix, some sufficient conditions are obtained to ensure that for an n-neuron neural network, there are exactly 3(k) equilibrium points with 0≤k≤n, among which 2(k) and 3(k)-2(k) equilibrium points are locally exponentially stable and unstable, respectively. Moreover, it concludes that all the states converge to one of the equilibrium points; i.e., the neural networks are completely stable. The derived conditions herein can be easily tested. Finally, a numerical example is given to illustrate the theoretical results. Copyright © 2016 Elsevier Ltd. All rights reserved.
Navigation of autonomous mobile robot using different activation functions of wavelet neural network
Directory of Open Access Journals (Sweden)
Panigrahi Pratap Kumar
2015-03-01
Full Text Available An autonomous mobile robot is a robot which can move and act autonomously without the help of human assistance. Navigation problem of mobile robot in unknown environment is an interesting research area. This is a problem of deducing a path for the robot from its initial position to a given goal position without collision with the obstacles. Different methods such as fuzzy logic, neural networks etc. are used to find collision free path for mobile robot. This paper examines behavior of path planning of mobile robot using three activation functions of wavelet neural network i.e. Mexican Hat, Gaussian and Morlet wavelet functions by MATLAB. The simulation result shows that WNN has faster learning speed with respect to traditional artificial neural network.
Computing single step operators of logic programming in radial basis function neural networks
Energy Technology Data Exchange (ETDEWEB)
Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong [School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Malaysia)
2014-07-10
Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (T{sub p}:I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks.
Energy Technology Data Exchange (ETDEWEB)
Koh, Hee Seok; Kim, Hyun Duck [Kyungnam University, Masan (Korea, Republic of); Lee, Kwang Seok [Chinju National University (Korea, Republic of)
1996-02-01
In this paper, we proposed an estimation method of a posterior probability and PDF(Probability density function) using a feed forward neural network and code books of VQ(vector quantization). In this study, We estimates a posterior probability and probability density function, which compose a new parameter with well-known Mel cepstrum and verificate the performance for the five vowels taking from syllables by NN(neural network) and PNN(probabilistic neural network). In case of new parameter, showed the best result by probabilistic neural network and recognition rates are average 83.02%. (author). 7 refs., 4 figs., 3 tabs.
Protein distance constraints predicted by neural networks and probability density functions
DEFF Research Database (Denmark)
Lund, Ole; Frimand, Kenneth; Gorodkin, Jan
1997-01-01
We predict interatomic C-α distances by two independent data driven methods. The first method uses statistically derived probability distributions of the pairwise distance between two amino acids, whilst the latter method consists of a neural network prediction approach equipped with windows taking....... The predictions are based on a data set derived using a new threshold similarity. We show that distances in proteins are predicted more accurately by neural networks than by probability density functions. We show that the accuracy of the predictions can be further increased by using sequence profiles. A threading...
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.
Cao, Renzhi; Freitas, Colton; Chan, Leong; Sun, Miao; Jiang, Haiqing; Chen, Zhangxin
2017-10-17
With the development of next generation sequencing techniques, it is fast and cheap to determine protein sequences but relatively slow and expensive to extract useful information from protein sequences because of limitations of traditional biological experimental techniques. Protein function prediction has been a long standing challenge to fill the gap between the huge amount of protein sequences and the known function. In this paper, we propose a novel method to convert the protein function problem into a language translation problem by the new proposed protein sequence language "ProLan" to the protein function language "GOLan", and build a neural machine translation model based on recurrent neural networks to translate "ProLan" language to "GOLan" language. We blindly tested our method by attending the latest third Critical Assessment of Function Annotation (CAFA 3) in 2016, and also evaluate the performance of our methods on selected proteins whose function was released after CAFA competition. The good performance on the training and testing datasets demonstrates that our new proposed method is a promising direction for protein function prediction. In summary, we first time propose a method which converts the protein function prediction problem to a language translation problem and applies a neural machine translation model for protein function prediction.
Directory of Open Access Journals (Sweden)
Petr Maca
2014-01-01
Full Text Available The presented paper aims to analyze the influence of the selection of transfer function and training algorithms on neural network flood runoff forecast. Nine of the most significant flood events, caused by the extreme rainfall, were selected from 10 years of measurement on small headwater catchment in the Czech Republic, and flood runoff forecast was investigated using the extensive set of multilayer perceptrons with one hidden layer of neurons. The analyzed artificial neural network models with 11 different activation functions in hidden layer were trained using 7 local optimization algorithms. The results show that the Levenberg-Marquardt algorithm was superior compared to the remaining tested local optimization methods. When comparing the 11 nonlinear transfer functions, used in hidden layer neurons, the RootSig function was superior compared to the rest of analyzed activation functions.
Sabour, Mohammad Reza; Moftakhari Anasori Movahed, Saman
2017-02-01
The soil sorption partition coefficient logKoc is an indispensable parameter that can be used in assessing the environmental risk of organic chemicals. In order to predict soil sorption partition coefficient for different and even unknown compounds in a fast and accurate manner, a radial basis function neural network (RBFNN) model was developed. Eight topological descriptors of 800 organic compounds were used as inputs of the model. These 800 organic compounds were chosen from a large and very diverse data set. Generalized Regression Neural Network (GRNN) was utilized as the function in this neural network model due to its capability to adapt very quickly. Hence, it can be used to predict logKoc for new chemicals, as well. Out of total data set, 560 organic compounds were used for training and 240 to test efficiency of the model. The obtained results indicate that the model performance is very well. The correlation coefficients (R2) for training and test sets were 0.995 and 0.933, respectively. The root-mean square errors (RMSE) were 0.2321 for training set and 0.413 for test set. As the results for both training and test set are extremely satisfactory, the proposed neural network model can be employed not only to predict logKoc of known compounds, but also to be adaptive for prediction of this value precisely for new products that enter the market each year. Copyright © 2016 Elsevier Ltd. All rights reserved.
QingJie, Wei; WenBin, Wang
2017-06-01
In this paper, the image retrieval using deep convolutional neural network combined with regularization and PRelu activation function is studied, and improves image retrieval accuracy. Deep convolutional neural network can not only simulate the process of human brain to receive and transmit information, but also contains a convolution operation, which is very suitable for processing images. Using deep convolutional neural network is better than direct extraction of image visual features for image retrieval. However, the structure of deep convolutional neural network is complex, and it is easy to over-fitting and reduces the accuracy of image retrieval. In this paper, we combine L1 regularization and PRelu activation function to construct a deep convolutional neural network to prevent over-fitting of the network and improve the accuracy of image retrieval
Radial basis function neural networks with sequential learning MRAN and its applications
Sundararajan, N; Wei Lu Ying
1999-01-01
This book presents in detail the newly developed sequential learning algorithm for radial basis function neural networks, which realizes a minimal network. This algorithm, created by the authors, is referred to as Minimal Resource Allocation Networks (MRAN). The book describes the application of MRAN in different areas, including pattern recognition, time series prediction, system identification, control, communication and signal processing. Benchmark problems from these areas have been studied, and MRAN is compared with other algorithms. In order to make the book self-contained, a review of t
Pinkham, Amy E; Hopfinger, Joseph B; Ruparel, Kosha; Penn, David L
2008-07-01
Previous work examining the neurobiological substrates of social cognition in healthy individuals has reported modulation of a social cognitive network such that increased activation of the amygdala, fusiform gyrus, and superior temporal sulcus are evident when individuals judge a face to be untrustworthy as compared with trustworthy. We examined whether this pattern would be present in individuals with schizophrenia who are known to show reduced activation within these same neural regions when processing faces. Additionally, we sought to determine how modulation of this social cognitive network may relate to social functioning. Neural activation was measured using functional magnetic resonance imaging with blood oxygenation level dependent contrast in 3 groups of individuals--nonparanoid individuals with schizophrenia, paranoid individuals with schizophrenia, and healthy controls--while they rated faces as either trustworthy or untrustworthy. Analyses of mean percent signal change extracted from a priori regions of interest demonstrated that both controls and nonparanoid individuals with schizophrenia showed greater activation of this social cognitive network when they rated a face as untrustworthy relative to trustworthy. In contrast, paranoid individuals did not show a significant difference in levels of activation based on how they rated faces. Further, greater activation of this social cognitive network to untrustworthy faces was significantly and positively correlated with social functioning. These findings indicate that impaired modulation of neural activity while processing social stimuli may underlie deficits in social cognition and social dysfunction in schizophrenia.
Could LC-NE-Dependent Adjustment of Neural Gain Drive Functional Brain Network Reorganization?
Directory of Open Access Journals (Sweden)
Carole Guedj
2017-01-01
Full Text Available The locus coeruleus-norepinephrine (LC-NE system is thought to act at synaptic, cellular, microcircuit, and network levels to facilitate cognitive functions through at least two different processes, not mutually exclusive. Accordingly, as a reset signal, the LC-NE system could trigger brain network reorganizations in response to salient information in the environment and/or adjust the neural gain within its target regions to optimize behavioral responses. Here, we provide evidence of the co-occurrence of these two mechanisms at the whole-brain level, in resting-state conditions following a pharmacological stimulation of the LC-NE system. We propose that these two mechanisms are interdependent such that the LC-NE-dependent adjustment of the neural gain inferred from the clustering coefficient could drive functional brain network reorganizations through coherence in the gamma rhythm. Via the temporal dynamic of gamma-range band-limited power, the release of NE could adjust the neural gain, promoting interactions only within the neuronal populations whose amplitude envelopes are correlated, thus making it possible to reorganize neuronal ensembles, functional networks, and ultimately, behavioral responses. Thus, our proposal offers a unified framework integrating the putative influence of the LC-NE system on both local- and long-range adjustments of brain dynamics underlying behavioral flexibility.
Circular antenna array pattern analysis using radial basis function neural network
Rama Sanjeeva Reddy, B.; Vakula, D.; Sarma, N. V. S. N.
2013-04-01
A method is proposed to design circular antenna array for the given gain and beam width using Artificial Neural Networks. In optimizing circular arrays, the parameters to be controlled are excitation of the elements, their separation, lengths and the circle radius. This paper deals about finding the parameters of radiation pattern of given uniform circular antenna array. Initially, the network is trained with a set of input-output data pairs. The trained network is used for testing. The training data set is generated from MATLAB simulation with number of elements N=5, 10, 15 and 20 elements of uniform circular array, respectively, distributed over a given circle, assuming 20 training cases. The number of input nodes, hidden nodes and output nodes are 20, 20 and 1, respectively. Predicted values of the neural network are compared with those of MATLAB simulation results and are found to be in agreement. This work establishes the application of Radial Basis Function Neural Network (RBFNN) for circular array pattern optimization. RBFNN is able to predict the output values with 97% of accuracy. This work proves that RBFNN can be used for circular antenna array design.
Functional Stem Cell Integration into Neural Networks Assessed by Organotypic Slice Cultures.
Forsberg, David; Thonabulsombat, Charoensri; Jäderstad, Johan; Jäderstad, Linda Maria; Olivius, Petri; Herlenius, Eric
2017-08-14
Re-formation or preservation of functional, electrically active neural networks has been proffered as one of the goals of stem cell-mediated neural therapeutics. A primary issue for a cell therapy approach is the formation of functional contacts between the implanted cells and the host tissue. Therefore, it is of fundamental interest to establish protocols that allow us to delineate a detailed time course of grafted stem cell survival, migration, differentiation, integration, and functional interaction with the host. One option for in vitro studies is to examine the integration of exogenous stem cells into an existing active neural network in ex vivo organotypic cultures. Organotypic cultures leave the structural integrity essentially intact while still allowing the microenvironment to be carefully controlled. This allows detailed studies over time of cellular responses and cell-cell interactions, which are not readily performed in vivo. This unit describes procedures for using organotypic slice cultures as ex vivo model systems for studying neural stem cell and embryonic stem cell engraftment and communication with CNS host tissue. © 2017 by John Wiley & Sons, Inc. Copyright © 2017 John Wiley & Sons, Inc.
Increased functional connectivity in intrinsic neural networks in individuals with aniridia
Pierce, Jordan E.; Krafft, Cynthia E.; Rodrigue, Amanda L.; Bobilev, Anastasia M.; Lauderdale, James D.; McDowell, Jennifer E.
2014-01-01
Mutations affecting the PAX6 gene result in aniridia, a condition characterized by the lack of an iris and other panocular defects. Among humans with aniridia, structural abnormalities also have been reported within the brain. The current study examined the functional implications of these deficits through “resting state” or task-free functional magnetic resonance imaging (fMRI) in 12 individuals with aniridia and 12 healthy age- and gender-matched controls. Using independent components analysis (ICA) and dual regression, individual patterns of functional connectivity associated with three intrinsic connectivity networks (ICNs; executive control, primary visual, and default mode) were compared across groups. In all three analyses, the aniridia group exhibited regions of greater connectivity correlated with the network, while the controls did not show any such regions. These differences suggest that individuals with aniridia recruit additional neural regions to supplement function in critical intrinsic networks, possibly due to inherent structural or sensory abnormalities related to the disorder. PMID:25566032
Increased functional connectivity in intrinsic neural networks in individuals with aniridia
Directory of Open Access Journals (Sweden)
Jordan Elisabeth Pierce
2014-12-01
Full Text Available Mutations affecting the PAX6 gene result in aniridia, a condition characterized by the lack of an iris and other panocular defects. Among humans with aniridia, structural abnormalities also have been reported within the brain. The current study examined the functional implications of these deficits through resting state or task-free functional magnetic resonance imaging in 12 individuals with aniridia and 12 healthy age- and gender-matched controls. Using independent components analysis and dual regression, individual patterns of functional connectivity associated with three intrinsic connectivity networks (executive control, primary visual, and default mode were compared across groups. In all three analyses, the aniridia group exhibited regions of greater connectivity correlated with the network, while the controls did not show any such regions. These differences suggest that individuals with aniridia recruit additional neural regions to supplement function in critical intrinsic networks, possibly due to inherent structural or sensory abnormalities related to the disorder.
Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.
Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji
2018-01-11
In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10 × 10 board, using TD(λ) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa(λ) agent with SiLU and dSiLU hidden units. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.
D'Souza, Adora M.; Abidin, Anas Zainul; Nagarajan, Mahesh B.; Wismüller, Axel
2016-03-01
We investigate the applicability of a computational framework, called mutual connectivity analysis (MCA), for directed functional connectivity analysis in both synthetic and resting-state functional MRI data. This framework comprises of first evaluating non-linear cross-predictability between every pair of time series prior to recovering the underlying network structure using community detection algorithms. We obtain the non-linear cross-prediction score between time series using Generalized Radial Basis Functions (GRBF) neural networks. These cross-prediction scores characterize the underlying functionally connected networks within the resting brain, which can be extracted using non-metric clustering approaches, such as the Louvain method. We first test our approach on synthetic models with known directional influence and network structure. Our method is able to capture the directional relationships between time series (with an area under the ROC curve = 0.92 +/- 0.037) as well as the underlying network structure (Rand index = 0.87 +/- 0.063) with high accuracy. Furthermore, we test this method for network recovery on resting-state fMRI data, where results are compared to the motor cortex network recovered from a motor stimulation sequence, resulting in a strong agreement between the two (Dice coefficient = 0.45). We conclude that our MCA approach is effective in analyzing non-linear directed functional connectivity and in revealing underlying functional network structure in complex systems.
Effects of transient unilateral functional brain disruption on global neural network status in rats
Directory of Open Access Journals (Sweden)
Willem M Otte
2014-03-01
Full Text Available Permanent focal brain damage can have critical effects on the function of nearby as well as remote brain regions. However, the effects of transient disturbances on global brain function are largely unknown. Our goal was to develop an experimental in vivo model to map the impact of transient functional brain impairment on large-scale neural networks in the absence of structural damage.We describe a new rat model of transient functional hemispheric disruption using unilateral focal anesthesia by intracarotid pentobarbital injection. The brain’s functional status was assessed with resting-state fMRI (rs-fMRI and EEG. We performed network analysis to identify and quantify highly connected network hubs, i.e. ‘rich-club organization’, in pre- and postbarbital functional networks.Perfusion MRI data demonstrated that the catheterized carotid artery predominantly supplied the ipsilateral hemisphere, allowing for selective hemispheric brain silencing. The prebarbital baseline network displayed strong functional connectivity within and between hemispheres. Following pentobarbital injection, the disrupted hemisphere revealed increased intrahemispheric functional connectivity with concomitant decrease of interhemispheric connectivity. The bilateral functional network was characterized by a strong positive rich-club effect, which was not affected by ipsilateral disruption. Nevertheless, the rich-club value was significantly decreased in the ipsilateral hemisphere and to a lesser extent contralaterally. Loss of interhemispheric EEG synchronization supported the rs-fMRI findings.Our data support the concept that densely connected rich-club regions play a central role in global brain communication, and show that network hub configurations can be significantly affected by focal temporary functional hemispheric disruption without structural neuronal damage. Further studies with this rat model will provide essential additional insights into network
Approximating quantum many-body wave functions using artificial neural networks
Cai, Zi; Liu, Jinguo
2018-01-01
In this paper, we demonstrate the expressibility of artificial neural networks (ANNs) in quantum many-body physics by showing that a feed-forward neural network with a small number of hidden layers can be trained to approximate with high precision the ground states of some notable quantum many-body systems. We consider the one-dimensional free bosons and fermions, spinless fermions on a square lattice away from half-filling, as well as frustrated quantum magnetism with a rapidly oscillating ground-state characteristic function. In the latter case, an ANN with a standard architecture fails, while that with a slightly modified one successfully learns the frustration-induced complex sign rule in the ground state and approximates the ground states with high precisions. As an example of practical use of our method, we also perform the variational method to explore the ground state of an antiferromagnetic J1-J2 Heisenberg model.
Directory of Open Access Journals (Sweden)
Dongliang Guo
2014-01-01
Full Text Available Indoor localization technique has received much attention in recent years. Many techniques have been developed to solve the problem. Among the recent proposed methods, radio frequency identification (RFID indoor localization technology has the advantages of low-cost, noncontact, non-line-of-sight, and high precision. This paper proposed two radial basis function (RBF neural network based indoor localization methods. The RBF neural networks are trained to learn the mapping relationship between received signal strength indication values and position of objects. Traditional method used the received signal strength directly as the input of neural network; we added another input channel by taking the difference of the received signal strength, thus improving the reliability and precision of positioning. Fuzzy clustering is used to determine the center of radial basis function. In order to reduce the impact of signal fading due to non-line-of-sight and multipath transmission in indoor environment, we improved the Gaussian filter to process received signal strength values. The experimental results show that the proposed method outperforms the existing methods as well as improves the reliability and precision of the RFID indoor positioning system.
Hoellinger, Thomas; Petieau, Mathieu; Duvinage, Matthieu; Castermans, Thierry; Seetharaman, Karthik; Cebolla, Ana-Maria; Bengoetxea, Ana; Ivanenko, Yuri; Dan, Bernard; Cheron, Guy
2013-01-01
The existence of dedicated neuronal modules such as those organized in the cerebral cortex, thalamus, basal ganglia, cerebellum, or spinal cord raises the question of how these functional modules are coordinated for appropriate motor behavior. Study of human locomotion offers an interesting field for addressing this central question. The coordination of the elevation of the 3 leg segments under a planar covariation rule (Borghese et al., 1996) was recently modeled (Barliya et al., 2009) by phase-adjusted simple oscillators shedding new light on the understanding of the central pattern generator (CPG) processing relevant oscillation signals. We describe the use of a dynamic recurrent neural network (DRNN) mimicking the natural oscillatory behavior of human locomotion for reproducing the planar covariation rule in both legs at different walking speeds. Neural network learning was based on sinusoid signals integrating frequency and amplitude features of the first three harmonics of the sagittal elevation angles of the thigh, shank, and foot of each lower limb. We verified the biological plausibility of the neural networks. Best results were obtained with oscillations extracted from the first three harmonics in comparison to oscillations outside the harmonic frequency peaks. Physiological replication steadily increased with the number of neuronal units from 1 to 80, where similarity index reached 0.99. Analysis of synaptic weighting showed that the proportion of inhibitory connections consistently increased with the number of neuronal units in the DRNN. This emerging property in the artificial neural networks resonates with recent advances in neurophysiology of inhibitory neurons that are involved in central nervous system oscillatory activities. The main message of this study is that this type of DRNN may offer a useful model of physiological central pattern generator for gaining insights in basic research and developing clinical applications.
Messé, Arnaud; Hütt, Marc-Thorsten; König, Peter; Hilgetag, Claus C.
2015-01-01
The relationship between the structural connectivity (SC) and functional connectivity (FC) of neural systems is a central focus in brain network science. It is an open question, however, how strongly the SC-FC relationship depends on specific topological features of brain networks or the models used for describing excitable dynamics. Using a basic model of discrete excitable units that follow a susceptible - excited - refractory dynamic cycle (SER model), we here analyze how functional connectivity is shaped by the topological features of a neural network, in particular its modularity. We compared the results obtained by the SER model with corresponding simulations by another well established dynamic mechanism, the Fitzhugh-Nagumo model, in order to explore general features of the SC-FC relationship. We showed that apparent discrepancies between the results produced by the two models can be resolved by adjusting the time window of integration of co-activations from which the FC is derived, providing a clearer distinction between co-activations and sequential activations. Thus, network modularity appears as an important factor shaping the FC-SC relationship across different dynamic models.
Huang, Wei; Oh, Sung-Kwun; Pedrycz, Witold
2014-12-01
In this study, we propose Hybrid Radial Basis Function Neural Networks (HRBFNNs) realized with the aid of fuzzy clustering method (Fuzzy C-Means, FCM) and polynomial neural networks. Fuzzy clustering used to form information granulation is employed to overcome a possible curse of dimensionality, while the polynomial neural network is utilized to build local models. Furthermore, genetic algorithm (GA) is exploited here to optimize the essential design parameters of the model (including fuzzification coefficient, the number of input polynomial fuzzy neurons (PFNs), and a collection of the specific subset of input PFNs) of the network. To reduce dimensionality of the input space, principal component analysis (PCA) is considered as a sound preprocessing vehicle. The performance of the HRBFNNs is quantified through a series of experiments, in which we use several modeling benchmarks of different levels of complexity (different number of input variables and the number of available data). A comparative analysis reveals that the proposed HRBFNNs exhibit higher accuracy in comparison to the accuracy produced by some models reported previously in the literature. Copyright © 2014 Elsevier Ltd. All rights reserved.
Shaping Early Reorganization of Neural Networks Promotes Motor Function after Stroke.
Volz, L J; Rehme, A K; Michely, J; Nettekoven, C; Eickhoff, S B; Fink, G R; Grefkes, C
2016-06-01
Neural plasticity is a major factor driving cortical reorganization after stroke. We here tested whether repetitively enhancing motor cortex plasticity by means of intermittent theta-burst stimulation (iTBS) prior to physiotherapy might promote recovery of function early after stroke. Functional magnetic resonance imaging (fMRI) was used to elucidate underlying neural mechanisms. Twenty-six hospitalized, first-ever stroke patients (time since stroke: 1-16 days) with hand motor deficits were enrolled in a sham-controlled design and pseudo-randomized into 2 groups. iTBS was administered prior to physiotherapy on 5 consecutive days either over ipsilesional primary motor cortex (M1-stimulation group) or parieto-occipital vertex (control-stimulation group). Hand motor function, cortical excitability, and resting-state fMRI were assessed 1 day prior to the first stimulation and 1 day after the last stimulation. Recovery of grip strength was significantly stronger in the M1-stimulation compared to the control-stimulation group. Higher levels of motor network connectivity were associated with better motor outcome. Consistently, control-stimulated patients featured a decrease in intra- and interhemispheric connectivity of the motor network, which was absent in the M1-stimulation group. Hence, adding iTBS to prime physiotherapy in recovering stroke patients seems to interfere with motor network degradation, possibly reflecting alleviation of post-stroke diaschisis. © The Author 2016. Published by Oxford University Press.
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
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
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.
A common functional neural network for overt production of speech and gesture.
Marstaller, L; Burianová, H
2015-01-22
The perception of co-speech gestures, i.e., hand movements that co-occur with speech, has been investigated by several studies. The results show that the perception of co-speech gestures engages a core set of frontal, temporal, and parietal areas. However, no study has yet investigated the neural processes underlying the production of co-speech gestures. Specifically, it remains an open question whether Broca's area is central to the coordination of speech and gestures as has been suggested previously. The objective of this study was to use functional magnetic resonance imaging to (i) investigate the regional activations underlying overt production of speech, gestures, and co-speech gestures, and (ii) examine functional connectivity with Broca's area. We hypothesized that co-speech gesture production would activate frontal, temporal, and parietal regions that are similar to areas previously found during co-speech gesture perception and that both speech and gesture as well as co-speech gesture production would engage a neural network connected to Broca's area. Whole-brain analysis confirmed our hypothesis and showed that co-speech gesturing did engage brain areas that form part of networks known to subserve language and gesture. Functional connectivity analysis further revealed a functional network connected to Broca's area that is common to speech, gesture, and co-speech gesture production. This network consists of brain areas that play essential roles in motor control, suggesting that the coordination of speech and gesture is mediated by a shared motor control network. Our findings thus lend support to the idea that speech can influence co-speech gesture production on a motoric level. Copyright © 2014 IBRO. Published by Elsevier Ltd. All rights reserved.
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 ...
An Index for Measuring Functional Diversity in Plant Communities Based on Neural Network Theory
Directory of Open Access Journals (Sweden)
Naiqi Song
2013-01-01
Full Text Available Functional diversity in plant communities is a key driver of ecosystem processes. The effective methods for measuring functional diversity are important in ecological studies. A new method based on neural network, self-organizing feature map (SOFM index, was put forward and described. A case application to the study of functional diversity of Phellodendron amurense communities in Xiaolongmen Forest Park of Beijing was carried out in this paper. The results showed that SOFM index was an effective method in the evaluation of functional diversity and its change in plant communities. Significant nonlinear correlations of SOFM index with the common used methods, FAD, MFAD, FDp, FDc, FRic, and FDiv indices, also proved that SOFM index is useful in the studies of functional diversity.
Functional and structural neural network characterization of serotonin transporter knockout rats.
Directory of Open Access Journals (Sweden)
Kajo van der Marel
Full Text Available Brain serotonin homeostasis is crucially maintained by the serotonin transporter (5-HTT, and its down-regulation has been linked to increased vulnerability for anxiety- and depression-related behavior. Studies in 5-HTT knockout (5-HTT(-/- rodents have associated inherited reduced functional expression of 5-HTT with increased sensitivity to adverse as well as rewarding environmental stimuli, and in particular cocaine hyperresponsivity. 5-HTT down-regulation may affect normal neuronal wiring of implicated corticolimbic cerebral structures. To further our understanding of its contribution to potential alterations in basal functional and structural properties of neural network configurations, we applied resting-state functional MRI (fMRI, pharmacological MRI of cocaine-induced activation, and diffusion tensor imaging (DTI in 5-HTT(-/- rats and wild-type controls (5-HTT(+/+. We found that baseline functional connectivity values and cocaine-induced neural activity within the corticolimbic network was not significantly altered in 5-HTT(-/- versus 5-HTT(+/+ rats. Similarly, DTI revealed mostly intact white matter structural integrity, except for a reduced fractional anisotropy in the genu of the corpus callosum of 5-HTT(-/- rats. At the macroscopic level, analyses of complex graphs constructed from either functional connectivity values or structural DTI-based tractography results revealed that key properties of brain network organization were essentially similar between 5-HTT(+/+ and 5-HTT(-/- rats. The individual tests for differences between 5-HTT(+/+ and 5-HTT(-/- rats were capable of detecting significant effects ranging from 5.8% (fractional anisotropy to 26.1% (pharmacological MRI and 29.3% (functional connectivity. Tentatively, lower fractional anisotropy in the genu of the corpus callosum could indicate a reduced capacity for information integration across hemispheres in 5-HTT(-/- rats. Overall, the comparison of 5-HTT(-/- and wild-type rats
Yamada, Kazunori D
2018-01-01
A profile-comparison method with position-specific scoring matrix (PSSM) is among the most accurate alignment methods. Currently, cosine similarity and correlation coefficients are used as scoring functions of dynamic programming to calculate similarity between PSSMs. However, it is unclear whether these functions are optimal for profile alignment methods. By definition, these functions cannot capture nonlinear relationships between profiles. Therefore, we attempted to discover a novel scoring function, which was more suitable for the profile-comparison method than existing functions, using neural networks. Although neural networks required derivative-of-cost functions, the problem being addressed in this study lacked them. Therefore, we implemented a novel derivative-free neural network by combining a conventional neural network with an evolutionary strategy optimization method used as a solver. Using this novel neural network system, we optimized the scoring function to align remote sequence pairs. Our results showed that the pairwise-profile aligner using the novel scoring function significantly improved both alignment sensitivity and precision relative to aligners using existing functions. We developed and implemented a novel derivative-free neural network and aligner (Nepal) for optimizing sequence alignments. Nepal improved alignment quality by adapting to remote sequence alignments and increasing the expressiveness of similarity scores. Additionally, this novel scoring function can be realized using a simple matrix operation and easily incorporated into other aligners. Moreover our scoring function could potentially improve the performance of homology detection and/or multiple-sequence alignment of remote homologous sequences. The goal of the study was to provide a novel scoring function for profile alignment method and develop a novel learning system capable of addressing derivative-free problems. Our system is capable of optimizing the performance of other
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.
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....
Tract-specific white matter hyperintensities disrupt neural network function in Alzheimer's disease.
Taylor, Alexander N W; Kambeitz-Ilankovic, Lana; Gesierich, Benno; Simon-Vermot, Lee; Franzmeier, Nicolai; Araque Caballero, Miguel Á; Müller, Sophia; Hesheng, Liu; Ertl-Wagner, Birgit; Bürger, Katharina; Weiner, Michael W; Dichgans, Martin; Duering, Marco; Ewers, Michael
2017-03-01
White matter hyperintensities (WMHs) increase the risk of Alzheimer's disease (AD). Whether WMHs are associated with the decline of functional neural networks in AD is debated. Resting-state functional magnetic resonance imaging and WMH were assessed in 78 subjects with increased amyloid levels on AV-45 positron emission tomography (PET) in different clinical stages of AD. We tested the association between WMH volume in major atlas-based fiber tract regions of interest (ROIs) and changes in functional connectivity (FC) between the tracts' projection areas within the default mode network (DMN). WMH volume within the inferior fronto-occipital fasciculus (IFOF) was the highest among all tract ROIs and associated with reduced FC in IFOF-connected DMN areas, independently of global AV-45 PET. Higher AV-45 PET contributed to reduced FC in IFOF-connected, temporal, and parietal DMN areas. High fiber tract WMH burden is associated with reduced FC in connected areas, thus adding to the effects of amyloid pathology on neuronal network function. Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.
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.
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...
Yan, Qin; Zhong, Yanfei
2008-12-01
The radial basis function (RBF) neural network is a powerful method for remote sensing image classification. It has a simple architecture and the learning algorithm corresponds to the solution of a linear regression problem, resulting in a fast training process. The main drawback of this strategy is the requirement of an efficient algorithm to determine the number, position, and dispersion of the RBF. Traditional methods to determine the centers are: randomly choose input vectors from the training data set; vectors obtained from unsupervised clustering algorithms, such as k-means, applied to the input data. These conduce that traditional RBF neural network is sensitive to the center initialization. In this paper, the artificial immune network (aiNet) model, a new computational intelligence based on artificial immune networks (AIN), is applied to obtain appropriate centers for remote sensing image classification. In the aiNet-RBF algorihtm, each input pattern corresonds to an antigenic stimulus, while each RBF candidate center is considered to be an element, or cell, of the immune network model. The steps are as follows: A set of candidate centers is initialized at random, where the initial number of candidates and their positions is not crucial to the performance. Then, the clonal selection principle will control which candidates will be selected and how they will be upadated. Note that the clonal selection principle will be responsible for how the centers will represent the training data set. Finally, the immune network will identify and eliminate or suppress self-recognizing individuals to control the number of candidate centers. After the above learning phase, the aiNet network centers represent internal images of the inuput patterns presented to it. The algorithm output is taken to be the matrix of memory cells' coordinates that represent the final centers to be adopted by the RBF network. The stopping criterion of the proposed algorithm is given by a pre
Ding, Xiaoshuai; Cao, Jinde; Alsaedi, Ahmed; Alsaadi, Fuad E; Hayat, Tasawar
2017-06-01
This paper is concerned with the fixed-time synchronization for a class of complex-valued neural networks in the presence of discontinuous activation functions and parameter uncertainties. Fixed-time synchronization not only claims that the considered master-slave system realizes synchronization within a finite time segment, but also requires a uniform upper bound for such time intervals for all initial synchronization errors. To accomplish the target of fixed-time synchronization, a novel feedback control procedure is designed for the slave neural networks. By means of the Filippov discontinuity theories and Lyapunov stability theories, some sufficient conditions are established for the selection of control parameters to guarantee synchronization within a fixed time, while an upper bound of the settling time is acquired as well, which allows to be modulated to predefined values independently on initial conditions. Additionally, criteria of modified controller for assurance of fixed-time anti-synchronization are also derived for the same system. An example is included to illustrate the proposed methodologies. Copyright © 2017 Elsevier Ltd. All rights reserved.
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.
Arshavsky, Yuri I
2016-09-22
The main paradigm of cognitive neuroscience is the connectionist concept postulating that the higher nervous activity is performed through interactions of neurons forming complex networks, whereas the function of individual neurons is restricted to generating electrical potentials and transmitting signals to other cells. In this article, I describe the observations from three fields-neurolinguistics, physiology of memory, and sensory perception-that can hardly be explained within the constraints of a purely connectionist concept. Rather, these examples suggest that cognitive functions are determined by specific properties of individual neurons and, therefore, are likely to be accomplished primarily at the intracellular level. This view is supported by the recent discovery that the brain's ability to create abstract concepts of particular individuals, animals, or places is performed by neurons ("concept cells") sparsely distributed in the medial temporal lobe. © The Author(s) 2016.
Directory of Open Access Journals (Sweden)
Eyad K Almaita
2017-03-01
Keywords: Energy efficiency, Power quality, Radial basis function, neural networks, adaptive, harmonic. Article History: Received Dec 15, 2016; Received in revised form Feb 2nd 2017; Accepted 13rd 2017; Available online How to Cite This Article: Almaita, E.K and Shawawreh J.Al (2017 Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm (On-Line Harmonics Estimation Application. International Journal of Renewable Energy Develeopment, 6(1, 9-17. http://dx.doi.org/10.14710/ijred.6.1.9-17
Directory of Open Access Journals (Sweden)
Moriah E. Thomason
2015-02-01
Full Text Available Formation of operational neural networks is one of the most significant accomplishments of human fetal brain growth. Recent advances in functional magnetic resonance imaging (fMRI have made it possible to obtain information about brain function during fetal development. Specifically, resting-state fMRI and novel signal covariation approaches have opened up a new avenue for non-invasive assessment of neural functional connectivity (FC before birth. Early studies in this area have unearthed new insights about principles of prenatal brain function. However, very little is known about the emergence and maturation of neural networks during fetal life. Here, we obtained cross-sectional rs-fMRI data from 39 fetuses between 24 and 38 weeks postconceptual age to examine patterns of connectivity across ten neural FC networks. We identified primitive forms of motor, visual, default mode, thalamic, and temporal networks in the human fetal brain. We discovered the first evidence of increased long-range, cerebral-cerebellar, cortical-subcortical, and intra-hemispheric FC with advancing fetal age. Continued aggregation of data about fundamental neural connectivity systems in utero is essential to establishing principles of connectomics at the beginning of human life. Normative data provides a vital context against which to compare instances of abnormal neurobiological development.
Cai, Zuowei; Huang, Lihong
2014-05-01
In this paper, we formulate and investigate a class of memristor-based BAM neural networks with time-varying delays. Under the framework of Filippov solutions, the viability and dissipativity of solutions for functional differential inclusions and memristive BAM neural networks can be guaranteed by the matrix measure approach and generalized Halanay inequalities. Then, a new method involving the application of set-valued version of Krasnoselskii' fixed point theorem in a cone is successfully employed to derive the existence of the positive periodic solution. The dynamic analysis in this paper utilizes the theory of set-valued maps and functional differential equations with discontinuous right-hand sides of Filippov type. The obtained results extend and improve some previous works on conventional BAM neural networks. Finally, numerical examples are given to demonstrate the theoretical results via computer simulations.
A Study of Artificial Neural Network Architectures for Othello Evaluation Functions
Binkley, Kevin J.; Seehart, Ken; Hagiwara, Masafumi
In this study, we use temporal difference learning (TDL) to investigate the ability of 20 different artificial neural network (ANN) architectures to learn othello game board evaluation functions. The ANN evaluation functions are applied to create a strong othello player using only 1-ply search. In addition to comparing many of the ANN architectures seen in the literature, we introduce several new architectures that consider the game board symmetry. Both embedding the game board symmetry into the network architecture through weight sharing and the outright removal of symmetry through symmetry removal are explored. Experiments varying the number of inputs per game board square from one to three, the number of hidden nodes, and number of hidden layers are also performed. We found it advantageous to consider game board symmetry in the form of symmetry by weight sharing; and that an input encoding of three inputs per square outperformed the one input per square encoding that is commonly seen in the literature. Furthermore, architectures with only one hidden layer were strongly outperformed by architectures with multiple hidden layers. A standard weighted-square board heuristic evaluation function from the literature was used to evaluate the quality of the trained ANN othello players. One of the ANN architectures introduced in this study, an ANN implementing weight sharing and consisting of three hidden layers, using only a 1-ply search, outperformed a weighted-square test heuristic player using a 6-ply minimax search.
Forecasting of PT. PLN (Persero) revenue using radial basis function neural network
Junior, Cindy Fajarianti; Suprijadi, Jadi; Franty, Yeny Krista
2017-03-01
PT. PLN (Persero) Distribusi Jakarta Raya (Disjaya) is a government-owned company that job is to maintain electricity distribution in Jakarta and Tangerang. The company's revenue can be seen from the pattern of the existing data, constantly increasing every year. This research aims to forecast company's revenue. The forecasting method using Artificial Neural Network method with Radial Basis Function (RBF) model based on historic data from January 2010 to December 2015. Based on the result of this research, the best model obtained (1-6-1) with composition 1 Neuron from input layer, 6 Neuron from hidden layer, and 1 Neuron output layer. The MAPE obtained with this model is 1.32 %.
Co-Operative Coevolutionary Neural Networks for Mining Functional Association Rules.
Wang, Bing; Merrick, Kathryn E; Abbass, Hussein A
2017-06-01
In this paper, we introduce a novel form of association rules (ARs) that do not require discretization of continuous variables or the use of intervals in either sides of the rule. This rule form captures nonlinear relationships among variables, and provides an alternative pattern representation for mining essential relations hidden in a given data set. We refer to the new rule form as a functional AR (FAR). A new neural network-based, co-operative, coevolutionary algorithm is presented for FAR mining. The algorithm is applied to both synthetic and real-world data sets, and its performance is analyzed. The experimental results show that the proposed mining algorithm is able to discover valid and essential underlying relations in the data. Comparison experiments are also carried out with the two state-of-the-art AR mining algorithms that can handle continuous variables to demonstrate the competitive performance of the proposed method.
Prediction of protein function using a deep convolutional neural network ensemble
Directory of Open Access Journals (Sweden)
Evangelia I. Zacharaki
2017-07-01
Full Text Available Background The availability of large databases containing high resolution three-dimensional (3D models of proteins in conjunction with functional annotation allows the exploitation of advanced supervised machine learning techniques for automatic protein function prediction. Methods In this work, novel shape features are extracted representing protein structure in the form of local (per amino acid distribution of angles and amino acid distances, respectively. Each of the multi-channel feature maps is introduced into a deep convolutional neural network (CNN for function prediction and the outputs are fused through support vector machines or a correlation-based k-nearest neighbor classifier. Two different architectures are investigated employing either one CNN per multi-channel feature set, or one CNN per image channel. Results Cross validation experiments on single-functional enzymes (n = 44,661 from the PDB database achieved 90.1% correct classification, demonstrating an improvement over previous results on the same dataset when sequence similarity was not considered. Discussion The automatic prediction of protein function can provide quick annotations on extensive datasets opening the path for relevant applications, such as pharmacological target identification. The proposed method shows promise for structure-based protein function prediction, but sufficient data may not yet be available to properly assess the method’s performance on non-homologous proteins and thus reduce the confounding factor of evolutionary relationships.
Li, Bo; Rui, Xiaoting
2018-01-01
Poor dispersion characteristics of rockets due to the vibration of Multiple Launch Rocket System (MLRS) have always restricted the MLRS development for several decades. Vibration control is a key technique to improve the dispersion characteristics of rockets. For a mechanical system such as MLRS, the major difficulty in designing an appropriate control strategy that can achieve the desired vibration control performance is to guarantee the robustness and stability of the control system under the occurrence of uncertainties and nonlinearities. To approach this problem, a computed torque controller integrated with a radial basis function neural network is proposed to achieve the high-precision vibration control for MLRS. In this paper, the vibration response of a computed torque controlled MLRS is described. The azimuth and elevation mechanisms of the MLRS are driven by permanent magnet synchronous motors and supposed to be rigid. First, the dynamic model of motor-mechanism coupling system is established using Lagrange method and field-oriented control theory. Then, in order to deal with the nonlinearities, a computed torque controller is designed to control the vibration of the MLRS when it is firing a salvo of rockets. Furthermore, to compensate for the lumped uncertainty due to parametric variations and un-modeled dynamics in the design of the computed torque controller, a radial basis function neural network estimator is developed to adapt the uncertainty based on Lyapunov stability theory. Finally, the simulated results demonstrate the effectiveness of the proposed control system and show that the proposed controller is robust with regard to the uncertainty.
Assessment of Global Voltage Stability Margin through Radial Basis Function Neural Network
Directory of Open Access Journals (Sweden)
Akash Saxena
2016-01-01
Full Text Available Dynamic operating conditions along with contingencies often present formidable challenges to the power engineers. Decisions pertaining to the control strategies taken by the system operators at energy management centre are based on the information about the system’s behavior. The application of ANN as a tool for voltage stability assessment is empirical because of its ability to do parallel data processing with high accuracy, fast response, and capability to model dynamic, nonlinear, and noisy data. This paper presents an effective methodology based on Radial Basis Function Neural Network (RBFN to predict Global Voltage Stability Margin (GVSM, for any unseen loading condition of the system. GVSM is used to assess the overall voltage stability status of the power system. A comparative analysis of different topologies of ANN, namely, Feedforward Backprop (FFBP, Cascade Forward Backprop (CFB, Generalized Regression (GR, Layer Recurrent (LR, Nonlinear Autoregressive Exogenous (NARX, ELMAN Backprop, and Feedforward Distributed Time Delay Network (FFDTDN, is carried out on the basis of capability of the prediction of GVSM. The efficacy of RBFN is better than other networks, which is validated by taking the predictions of GVSM at different levels of Additive White Gaussian Noise (AWGN in input features. The results obtained from ANNs are validated through the offline Newton Raphson (N-R method. The proposed methodology is tested over IEEE 14-bus, IEEE 30-bus, and IEEE 118-bus test systems.
Chen, Jiajia; Zhao, Pan; Liang, Huawei; Mei, Tao
2014-09-18
The autonomous vehicle is an automated system equipped with features like environment perception, decision-making, motion planning, and control and execution technology. Navigating in an unstructured and complex environment is a huge challenge for autonomous vehicles, due to the irregular shape of road, the requirement of real-time planning, and the nonholonomic constraints of vehicle. This paper presents a motion planning method, based on the Radial Basis Function (RBF) neural network, to guide the autonomous vehicle in unstructured environments. The proposed algorithm extracts the drivable region from the perception grid map based on the global path, which is available in the road network. The sample points are randomly selected in the drivable region, and a gradient descent method is used to train the RBF network. The parameters of the motion-planning algorithm are verified through the simulation and experiment. It is observed that the proposed approach produces a flexible, smooth, and safe path that can fit any road shape. The method is implemented on autonomous vehicle and verified against many outdoor scenes; furthermore, a comparison of proposed method with the existing well-known Rapidly-exploring Random Tree (RRT) method is presented. The experimental results show that the proposed method is highly effective in planning the vehicle path and offers better motion quality.
Large-scale functional neural network correlates of response inhibition: an fMRI meta-analysis.
Zhang, Ruibin; Geng, Xiujuan; Lee, Tatia M C
2017-12-01
An influential hypothesis from the last decade proposed that regions within the right inferior frontal cortex of the human brain were dedicated to supporting response inhibition. There is growing evidence, however, to support an alternative model, which proposes that neural areas associated with specific inhibitory control tasks co-exist as common network mechanisms, supporting diverse cognitive processes. This meta-analysis of 225 studies comprising 323 experiments examined the common and distinct neural correlates of cognitive processes for response inhibition, namely interference resolution, action withholding, and action cancellation. Activation coordinates for each subcategory were extracted using multilevel kernel density analysis (MKDA). The extracted activity patterns were then mapped onto the brain functional network atlas to derive the common (i.e., process-general) and distinct (i.e., domain-oriented) neural network correlates of these processes. Independent of the task types, activation of the right hemispheric regions (inferior frontal gyrus, insula, median cingulate, and paracingulate gyri) and superior parietal gyrus was common across the cognitive processes studied. Mapping the activation patterns to a brain functional network atlas revealed that the fronto-parietal and ventral attention networks were the core neural systems that were commonly engaged in different processes of response inhibition. Subtraction analyses elucidated the distinct neural substrates of interference resolution, action withholding, and action cancellation, revealing stronger activation in the ventral attention network for interference resolution than action inhibition. On the other hand, action withholding/cancellation primarily engaged the fronto-striatal circuit. Overall, our results suggest that response inhibition is a multidimensional cognitive process involving multiple neural regions and networks for coordinating optimal performance. This finding has significant
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.
Kayri, Murat
2015-01-01
The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The…
Institute of Scientific and Technical Information of China (English)
ZHOU Li-Ming; CHEN Tian-Lun
2004-01-01
Based on the standard self-organizing map neural network model and an integrate-and-tire mechanism, we investigate the effect of the nonlinear interactive function on the self-organized criticality in our model. Based on these we also investigate the effect of the refractoryperiod on the self-organized criticality of the system.
Nie, Xiaobing; Zheng, Wei Xing
2015-05-01
This paper is concerned with the problem of coexistence and dynamical behaviors of multiple equilibrium points for neural networks with discontinuous non-monotonic piecewise linear activation functions and time-varying delays. The fixed point theorem and other analytical tools are used to develop certain sufficient conditions that ensure that the n-dimensional discontinuous neural networks with time-varying delays can have at least 5(n) equilibrium points, 3(n) of which are locally stable and the others are unstable. The importance of the derived results is that it reveals that the discontinuous neural networks can have greater storage capacity than the continuous ones. Moreover, different from the existing results on multistability of neural networks with discontinuous activation functions, the 3(n) locally stable equilibrium points obtained in this paper are located in not only saturated regions, but also unsaturated regions, due to the non-monotonic structure of discontinuous activation functions. A numerical simulation study is conducted to illustrate and support the derived theoretical results. Copyright © 2015 Elsevier Ltd. All rights reserved.
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. .
Stateczny, A.; Lubczonek, J.
2003-04-01
The basic problem in the construction of a numerical spatial sea chart is such transformation of the sounding data that it should be possible to determine the depth at any point of the bottom area. In recent years, much attention has been devoted to the problem of modelling the seabed shape in a numerical three-dimensional sea chart. Various methods for modelling the seabed shape are applied. These methods can be divided into analytical and neural. In the case of applying the model for navigational tasks, the selection of a suitable method should ensure high accuracy of surface projection. The model should be conformed to the surface shape, spatial distribution of the measurement points and their number. The application of universal methods like 'multiquadric' or 'kriging' does not ensure an optimal result either, as each of these methods can have a certain number of options and parameters, which frequently play a significant role during surface modelling. It is often difficult to optimise these factors and even experience does not guarantee a satisfactory result. This applies especially to modelling irregular surfaces, when it is difficult to select the method suitable for the surface shape that is sometimes unpredictable. It has been suggested that the method of selecting the shape parameter of the radial basis functions should be applied which makes it possible to minimise the mean square error of the approximated surface. The paper presents a new method of optimising the parameters of radial functions used for modelling the bottom surface. The accuracy of the surface projection obtained was the criterion for optimisation. The properties of self-organizing networks created the possibility of selecting testing points out of any set of measurement points and the determination of the minimum value of RMS error by means of the GRNN network. Optimisation of the shape parameter required building the proper polygon of the test points. For building such kind of polygon
Directory of Open Access Journals (Sweden)
Ya-li Zhou
2009-01-01
Full Text Available In practical active noise control (ANC systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have nonminimum-phase response. A linear controller under such situations yields poor performance. A novel functional link artificial neural network (FLANN-based simultaneous perturbation stochastic approximation (SPSA algorithm, which functions as a nonlinear mode-free (MF controller, is proposed in this paper. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS algorithm, and performs better than the recently proposed filtered-s least mean square (FSLMS algorithm when the secondary path is time-varying. This observation implies that the SPSA-based MF controller can eliminate the need of the modeling of the secondary path for the ANC system.
A simple structure wavelet transform circuit employing function link neural networks and SI filters
Mu, Li; Yigang, He
2016-12-01
Signal processing by means of analog circuits offers advantages from a power consumption viewpoint. Implementing wavelet transform (WT) using analog circuits is of great interest when low-power consumption becomes an important issue. In this article, a novel simple structure WT circuit in analog domain is presented by employing functional link neural network (FLNN) and switched-current (SI) filters. First, the wavelet base is approximated using FLNN algorithms for giving a filter transfer function that is suitable for simple structure WT circuit implementation. Next, the WT circuit is constructed with the wavelet filter bank, whose impulse response is the approximated wavelet and its dilations. The filter design that follows is based on a follow-the-leader feedback (FLF) structure with multiple output bilinear SI integrators and current mirrors as the main building blocks. SI filter is well suited for this application since the dilation constant across different scales of the transform can be precisely implemented and controlled by the clock frequency of the circuit with the same system architecture. Finally, to illustrate the design procedure, a seventh-order FLNN-approximated Gaussian wavelet is implemented as an example. Simulations have successfully verified that the designed simple structure WT circuit has low sensitivity, low-power consumption and litter effect to the imperfections.
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.
Yoo, Sung-Hoon; Oh, Sung-Kwun; Pedrycz, Witold
2015-09-01
In this study, we propose a hybrid method of face recognition by using face region information extracted from the detected face region. In the preprocessing part, we develop a hybrid approach based on the Active Shape Model (ASM) and the Principal Component Analysis (PCA) algorithm. At this step, we use a CCD (Charge Coupled Device) camera to acquire a facial image by using AdaBoost and then Histogram Equalization (HE) is employed to improve the quality of the image. ASM extracts the face contour and image shape to produce a personal profile. Then we use a PCA method to reduce dimensionality of face images. In the recognition part, we consider the improved Radial Basis Function Neural Networks (RBF NNs) to identify a unique pattern associated with each person. The proposed RBF NN architecture consists of three functional modules realizing the condition phase, the conclusion phase, and the inference phase completed with the help of fuzzy rules coming in the standard 'if-then' format. In the formation of the condition part of the fuzzy rules, the input space is partitioned with the use of Fuzzy C-Means (FCM) clustering. In the conclusion part of the fuzzy rules, the connections (weights) of the RBF NNs are represented by four kinds of polynomials such as constant, linear, quadratic, and reduced quadratic. The values of the coefficients are determined by running a gradient descent method. The output of the RBF NNs model is obtained by running a fuzzy inference method. The essential design parameters of the network (including learning rate, momentum coefficient and fuzzification coefficient used by the FCM) are optimized by means of Differential Evolution (DE). The proposed P-RBF NNs (Polynomial based RBF NNs) are applied to facial recognition and its performance is quantified from the viewpoint of the output performance and recognition rate. Copyright © 2015 Elsevier Ltd. All rights reserved.
Meghabghab, George
2001-01-01
Discusses the evaluation of search engines and uses neural networks in stochastic simulation of the number of rejected Web pages per search query. Topics include the iterative radial basis functions (RBF) neural network; precision; response time; coverage; Boolean logic; regression models; crawling algorithms; and implications for search engine…
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.
Testolin, Alberto; Zorzi, Marco
2016-01-01
Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage.
Directory of Open Access Journals (Sweden)
Alberto Testolin
2016-07-01
Full Text Available Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage.
Cost-Sensitive Radial Basis Function Neural Network Classifier for Software Defect Prediction
Directory of Open Access Journals (Sweden)
P. Kumudha
2016-01-01
Full Text Available Effective prediction of software modules, those that are prone to defects, will enable software developers to achieve efficient allocation of resources and to concentrate on quality assurance activities. The process of software development life cycle basically includes design, analysis, implementation, testing, and release phases. Generally, software testing is a critical task in the software development process wherein it is to save time and budget by detecting defects at the earliest and deliver a product without defects to the customers. This testing phase should be carefully operated in an effective manner to release a defect-free (bug-free software product to the customers. In order to improve the software testing process, fault prediction methods identify the software parts that are more noted to be defect-prone. This paper proposes a prediction approach based on conventional radial basis function neural network (RBFNN and the novel adaptive dimensional biogeography based optimization (ADBBO model. The developed ADBBO based RBFNN model is tested with five publicly available datasets from the NASA data program repository. The computed results prove the effectiveness of the proposed ADBBO-RBFNN classifier approach with respect to the considered metrics in comparison with that of the early predictors available in the literature for the same datasets.
Directory of Open Access Journals (Sweden)
Amir LAKZIAN
2010-09-01
Full Text Available This paper presents the comparison of three different approaches to estimate soil water content at defined values of soil water potential based on selected parameters of soil solid phase. Forty different sampling locations in northeast of Iran were selected and undisturbed samples were taken to measure the water content at field capacity (FC, -33 kPa, and permanent wilting point (PWP, -1500 kPa. At each location solid particle of each sample including the percentage of sand, silt and clay were measured. Organic carbon percentage and soil texture were also determined for each soil sample at each location. Three different techniques including pattern recognition approach (k nearest neighbour, k-NN, Artificial Neural Network (ANN and pedotransfer functions (PTF were used to predict the soil water at each sampling location. Mean square deviation (MSD and its components, index of agreement (d, root mean square difference (RMSD and normalized RMSD (RMSDr were used to evaluate the performance of all the three approaches. Our results showed that k-NN and PTF performed better than ANN in prediction of water content at both FC and PWP matric potential. Various statistics criteria for simulation performance also indicated that between kNN and PTF, the former, predicted water content at PWP more accurate than PTF, however both approach showed a similar accuracy to predict water content at FC.
Cost-Sensitive Radial Basis Function Neural Network Classifier for Software Defect Prediction.
Kumudha, P; Venkatesan, R
Effective prediction of software modules, those that are prone to defects, will enable software developers to achieve efficient allocation of resources and to concentrate on quality assurance activities. The process of software development life cycle basically includes design, analysis, implementation, testing, and release phases. Generally, software testing is a critical task in the software development process wherein it is to save time and budget by detecting defects at the earliest and deliver a product without defects to the customers. This testing phase should be carefully operated in an effective manner to release a defect-free (bug-free) software product to the customers. In order to improve the software testing process, fault prediction methods identify the software parts that are more noted to be defect-prone. This paper proposes a prediction approach based on conventional radial basis function neural network (RBFNN) and the novel adaptive dimensional biogeography based optimization (ADBBO) model. The developed ADBBO based RBFNN model is tested with five publicly available datasets from the NASA data program repository. The computed results prove the effectiveness of the proposed ADBBO-RBFNN classifier approach with respect to the considered metrics in comparison with that of the early predictors available in the literature for the same datasets.
Impaired neural networks for approximate calculation in dyscalculic children: a functional MRI study
Directory of Open Access Journals (Sweden)
Dosch Mengia
2006-09-01
Full Text Available Abstract Background Developmental dyscalculia (DD is a specific learning disability affecting the acquisition of mathematical skills in children with otherwise normal general intelligence. The goal of the present study was to examine cerebral mechanisms underlying DD. Methods Eighteen children with DD aged 11.2 ± 1.3 years and twenty age-matched typically achieving schoolchildren were investigated using functional magnetic resonance imaging (fMRI during trials testing approximate and exact mathematical calculation, as well as magnitude comparison. Results Children with DD showed greater inter-individual variability and had weaker activation in almost the entire neuronal network for approximate calculation including the intraparietal sulcus, and the middle and inferior frontal gyrus of both hemispheres. In particular, the left intraparietal sulcus, the left inferior frontal gyrus and the right middle frontal gyrus seem to play crucial roles in correct approximate calculation, since brain activation correlated with accuracy rate in these regions. In contrast, no differences between groups could be found for exact calculation and magnitude comparison. In general, fMRI revealed similar parietal and prefrontal activation patterns in DD children compared to controls for all conditions. Conclusion In conclusion, there is evidence for a deficient recruitment of neural resources in children with DD when processing analog magnitudes of numbers.
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.
Ayala, Helon Vicente Hultmann; Coelho, Leandro dos Santos
2016-02-01
The present work introduces a procedure for input selection and parameter estimation for system identification based on Radial Basis Functions Neural Networks (RBFNNs) models with an improved objective function based on the residuals and its correlation function coefficients. We show the results when the proposed methodology is applied to model a magnetorheological damper, with real acquired data, and other two well-known benchmarks. The canonical genetic and differential evolution algorithms are used in cascade to decompose the problem of defining the lags taken as the inputs of the model and its related parameters based on the simultaneous minimization of the residuals and higher orders correlation functions. The inner layer of the cascaded approach is composed of a population which represents the lags on the inputs and outputs of the system and an outer layer represents the corresponding parameters of the RBFNN. The approach is able to define both the inputs of the model and its parameters. This is interesting as it frees the designer of manual procedures, which are time consuming and prone to error, usually done to define the model inputs. We compare the proposed methodology with other works found in the literature, showing overall better results for the cascaded approach.
Islam, Md Monirul; Sattar, Md Abdus; Amin, Md Faijul; Yao, Xin; Murase, Kazuyuki
2009-12-01
The generalization ability of artificial neural networks (ANNs) is greatly dependent on their architectures. Constructive algorithms provide an attractive automatic way of determining a near-optimal ANN architecture for a given problem. Several such algorithms have been proposed in the literature and shown their effectiveness. This paper presents a new constructive algorithm (NCA) in automatically determining ANN architectures. Unlike most previous studies on determining ANN architectures, NCA puts emphasis on architectural adaptation and functional adaptation in its architecture determination process. It uses a constructive approach to determine the number of hidden layers in an ANN and of neurons in each hidden layer. To achieve functional adaptation, NCA trains hidden neurons in the ANN by using different training sets that were created by employing a similar concept used in the boosting algorithm. The purpose of using different training sets is to encourage hidden neurons to learn different parts or aspects of the training data so that the ANN can learn the whole training data in a better way. In this paper, the convergence and computational issues of NCA are analytically studied. The computational complexity of NCA is found to be O(W xP(t) xtau), where W is the number of weights in the ANN, P(t) is the number of training examples, and tau is the number of training epochs. This complexity has the same order as what the backpropagation learning algorithm requires for training a fixed ANN architecture. A set of eight classification and two approximation benchmark problems was used to evaluate the performance of NCA. The experimental results show that NCA can produce ANN architectures with fewer hidden neurons and better generalization ability compared to existing constructive and nonconstructive algorithms.
Energy Technology Data Exchange (ETDEWEB)
Nishitani, Y.; Kaneko, Y.; Ueda, M.; Fujii, E. [Advanced Technology Research Laboratories, Panasonic Corporation, Seika, Kyoto 619-0237 (Japan); Morie, T. [Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Wakamatsu-ku, Kitakyushu 808-0196 (Japan)
2012-06-15
Spike-timing-dependent synaptic plasticity (STDP) is demonstrated in a synapse device based on a ferroelectric-gate field-effect transistor (FeFET). STDP is a key of the learning functions observed in human brains, where the synaptic weight changes only depending on the spike timing of the pre- and post-neurons. The FeFET is composed of the stacked oxide materials with ZnO/Pr(Zr,Ti)O{sub 3} (PZT)/SrRuO{sub 3}. In the FeFET, the channel conductance can be altered depending on the density of electrons induced by the polarization of PZT film, which can be controlled by applying the gate voltage in a non-volatile manner. Applying a pulse gate voltage enables the multi-valued modulation of the conductance, which is expected to be caused by a change in PZT polarization. This variation depends on the height and the duration of the pulse gate voltage. Utilizing these characteristics, symmetric and asymmetric STDP learning functions are successfully implemented in the FeFET-based synapse device by applying the non-linear pulse gate voltage generated from a set of two pulses in a sampling circuit, in which the two pulses correspond to the spikes from the pre- and post-neurons. The three-terminal structure of the synapse device enables the concurrent learning, in which the weight update can be performed without canceling signal transmission among neurons, while the neural networks using the previously reported two-terminal synapse devices need to stop signal transmission for learning.
Qiao, Jun-Fei; Han, Hong-Gui
2010-02-01
This paper presents a repair algorithm for the design of a Radial Basis Function (RBF) neural network. The proposed repair RBF (RRBF) algorithm starts from a single prototype randomly initialized in the feature space. The algorithm has two main phases: an architecture learning phase and a parameter adjustment phase. The architecture learning phase uses a repair strategy based on a sensitivity analysis (SA) of the network's output to judge when and where hidden nodes should be added to the network. New nodes are added to repair the architecture when the prototype does not meet the requirements. The parameter adjustment phase uses an adjustment strategy where the capabilities of the network are improved by modifying all the weights. The algorithm is applied to two application areas: approximating a non-linear function, and modeling the key parameter, chemical oxygen demand (COD) used in the waste water treatment process. The results of simulation show that the algorithm provides an efficient solution to both problems.
Zhou, Miaolei; Wang, Yifan; Xu, Rui; Zhang, Qi; Zhu, Dong
2017-06-16
Hysteresis exists in magnetic shape memory alloy (MSMA) actuators, which restricts MSMA actuators' application. To describe hysteresis of the MSMA actuators, a hysteresis model based on the radial basis function neural network (RBFNN) is put forward. Then, an inverse RBFNN model is set up, and it is compared with the inverse model based on the traditional cut-and-try method. Finally, to solve hysteresis of the actuators, an inverse model for MSMA actuators is used to build feed-forward controller. Simulation results show the maximum modeling error for inverse hysteresis model designed by neural network is 0.79% and compared with traditional cut-and-try method, the maximum modeling error decreases by 1.85%. The maximum tracking error rate of feed-forward control is 0.38%. The hysteresis of MSMA actuators is reduced. By using the feed-forward controller, high precision control is achieved.
Directory of Open Access Journals (Sweden)
M. Kumar
2016-01-01
Full Text Available Gaussian noise is one of the dominant noises, which degrades the quality of acquired Computed Tomography (CT image data. It creates difficulties in pathological identification or diagnosis of any disease. Gaussian noise elimination is desirable to improve the clarity of a CT image for clinical, diagnostic, and postprocessing applications. This paper proposes an evolutionary nonlinear adaptive filter approach, using Cat Swarm Functional Link Artificial Neural Network (CS-FLANN to remove the unwanted noise. The structure of the proposed filter is based on the Functional Link Artificial Neural Network (FLANN and the Cat Swarm Optimization (CSO is utilized for the selection of optimum weight of the neural network filter. The applied filter has been compared with the existing linear filters, like the mean filter and the adaptive Wiener filter. The performance indices, such as peak signal to noise ratio (PSNR, have been computed for the quantitative analysis of the proposed filter. The experimental evaluation established the superiority of the proposed filtering technique over existing methods.
Hsu, Ching-Chi; Lin, Jinn; Chao, Ching-Kong
2011-12-01
Optimizing the orthopaedic screws can greatly improve their biomechanical performances. However, a methodical design optimization approach requires a long time to search the best design. Thus, the surrogate objective functions of the orthopaedic screws should be accurately developed. To our knowledge, there is no study to evaluate the strengths and limitations of the surrogate methods in developing the objective functions of the orthopaedic screws. Three-dimensional finite element models for both the tibial locking screws and the spinal pedicle screws were constructed and analyzed. Then, the learning data were prepared according to the arrangement of the Taguchi orthogonal array, and the verification data were selected with use of a randomized selection. Finally, the surrogate objective functions were developed by using either the multiple linear regression or the artificial neural network. The applicability and accuracy of those surrogate methods were evaluated and discussed. The multiple linear regression method could successfully construct the objective function of the tibial locking screws, but it failed to develop the objective function of the spinal pedicle screws. The artificial neural network method showed a greater capacity of prediction in developing the objective functions for the tibial locking screws and the spinal pedicle screws than the multiple linear regression method. The artificial neural network method may be a useful option for developing the objective functions of the orthopaedic screws with a greater structural complexity. The surrogate objective functions of the orthopaedic screws could effectively decrease the time and effort required for the design optimization process. Copyright Â© 2010 Elsevier Ireland Ltd. All rights reserved.
Dawson, Neil; Xiao, Xiaolin; McDonald, Martin; Higham, Desmond J; Morris, Brian J; Pratt, Judith A
2014-02-01
Compromised functional integration between cerebral subsystems and dysfunctional brain network organization may underlie the neurocognitive deficits seen in psychiatric disorders. Applying topological measures from network science to brain imaging data allows the quantification of complex brain network connectivity. While this approach has recently been used to further elucidate the nature of brain dysfunction in schizophrenia, the value of applying this approach in preclinical models of psychiatric disease has not been recognized. For the first time, we apply both established and recently derived algorithms from network science (graph theory) to functional brain imaging data from rats treated subchronically with the N-methyl-D-aspartic acid (NMDA) receptor antagonist phencyclidine (PCP). We show that subchronic PCP treatment induces alterations in the global properties of functional brain networks akin to those reported in schizophrenia. Furthermore, we show that subchronic PCP treatment induces compromised functional integration between distributed neural systems, including between the prefrontal cortex and hippocampus, that have established roles in cognition through, in part, the promotion of thalamic dysconnectivity. We also show that subchronic PCP treatment promotes the functional disintegration of discrete cerebral subsystems and also alters the connectivity of neurotransmitter systems strongly implicated in schizophrenia. Therefore, we propose that sustained NMDA receptor hypofunction contributes to the pathophysiology of dysfunctional brain network organization in schizophrenia.
[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.
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
Pennington, Robert S.; Coll, Catalina; Estradé, Sònia; Peiró, Francesca; Koch, Christoph T.
2018-01-01
Iterative neural-network-based three-dimensional structural optimization of atomic positions over tens of nanometers is performed using transmission electron microscope (TEM) diffraction data simulated from density functional theory (DFT) all-electron densities, thus retrieving parameter variations along the beam direction. We first use experimental data to show that the GPAW DFT code's all-electron densities are considerably more accurate for electron diffraction calculations compared to conventional isolated-atom scattering factors, and they also compare well to Wien2K DFT simulations. This DFT-TEM combination is then integrated into an iterative neural-network-optimization-based algorithm (PRIMES, parameter retrieval and inversion from multiple electron scattering) to retrieve nanometer-scale ferroelectric polarization domains and strain in theoretical bulklike specimens from TEM data. DFT and isolated-atom methods produce substantially different diffraction patterns and retrieved polarization domain parameters, and DFT is sufficient to retrieve strain properties from a silicon specimen simulated using experimentally derived structure factors. Thus, we show that the improved accuracy, fast computation, and intuitive integration make the GPAW DFT code well suited for three-dimensional materials characterization and demonstrate this using an iterative neural-network algorithm that is verifiable on the mesoscale and, with DFT integration, self-consistent on the nanoscale.
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...
Directory of Open Access Journals (Sweden)
Satoru Hiwa
2016-01-01
Full Text Available Functional near-infrared spectroscopy (fNIRS is suitable for noninvasive mapping of relative changes in regional cortical activity but is limited for quantitative comparisons among cortical sites, subjects, and populations. We have developed a convolutional neural network (CNN analysis method that learns feature vectors for accurate identification of group differences in fNIRS responses. In this study, subject gender was classified using CNN analysis of fNIRS data. fNIRS data were acquired from male and female subjects during a visual number memory task performed in a white noise environment because previous studies had revealed that the pattern of cortical blood flow during the task differed between males and females. A learned classifier accurately distinguished males from females based on distinct fNIRS signals from regions of interest (ROI including the inferior frontal gyrus and premotor areas that were identified by the learning algorithm. These cortical regions are associated with memory storage, attention, and task motor response. The accuracy of the classifier suggests stable gender-based differences in cerebral blood flow during this task. The proposed CNN analysis method can objectively identify ROIs using fNIRS time series data for machine learning to distinguish features between groups.
Ding, Zhixia; Zeng, Zhigang; Wang, Leimin
2017-03-10
This paper is concerned with robust finite-time stabilization for a class of fractional-order neural networks (FNNs) with two types of activation functions (i.e., discontinuous and continuous activation function) under uncertainty. It is worth noting that there exist few results about FNNs with discontinuous activation functions, which is mainly because classical solutions and theories of differential equations cannot be applied in this case. Especially, there is no relevant finite-time stabilization research for such system, and this paper makes up for the gap. The existence of global solution under the framework of Filippov for such system is guaranteed by limiting discontinuous activation functions. According to set-valued analysis and Kakutani's fixed point theorem, we obtain the existence of equilibrium point. In particular, based on differential inclusion theory and fractional Lyapunov stability theory, several new sufficient conditions are given to ensure finite-time stabilization via a novel discontinuous controller, and the upper bound of the settling time for stabilization is estimated. In addition, we analyze the finite-time stabilization of FNNs with Lipschitz-continuous activation functions under uncertainty. The results of this paper improve corresponding ones of integer-order neural networks with discontinuous and continuous activation functions. Finally, three numerical examples are given to show the effectiveness of the theoretical results.
Directory of Open Access Journals (Sweden)
van der Flier Wiesje M
2009-08-01
Full Text Available Abstract Background Although a large body of knowledge about both brain structure and function has been gathered over the last decades, we still have a poor understanding of their exact relationship. Graph theory provides a method to study the relation between network structure and function, and its application to neuroscientific data is an emerging research field. We investigated topological changes in large-scale functional brain networks in patients with Alzheimer's disease (AD and frontotemporal lobar degeneration (FTLD by means of graph theoretical analysis of resting-state EEG recordings. EEGs of 20 patients with mild to moderate AD, 15 FTLD patients, and 23 non-demented individuals were recorded in an eyes-closed resting-state. The synchronization likelihood (SL, a measure of functional connectivity, was calculated for each sensor pair in 0.5–4 Hz, 4–8 Hz, 8–10 Hz, 10–13 Hz, 13–30 Hz and 30–45 Hz frequency bands. The resulting connectivity matrices were converted to unweighted graphs, whose structure was characterized with several measures: mean clustering coefficient (local connectivity, characteristic path length (global connectivity and degree correlation (network 'assortativity'. All results were normalized for network size and compared with random control networks. Results In AD, the clustering coefficient decreased in the lower alpha and beta bands (p Conclusion With decreasing local and global connectivity parameters, the large-scale functional brain network organization in AD deviates from the optimal 'small-world' network structure towards a more 'random' type. This is associated with less efficient information exchange between brain areas, supporting the disconnection hypothesis of AD. Surprisingly, FTLD patients show changes in the opposite direction, towards a (perhaps excessively more 'ordered' network structure, possibly reflecting a different underlying pathophysiological process.
Neural Networks for Optimal Control
DEFF Research Database (Denmark)
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
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 ...
Application of radial basis neural network for state estimation of ...
African Journals Online (AJOL)
user
An original application of radial basis function (RBF) neural network for power system state estimation is proposed in this paper. The property of massive parallelism of neural networks is employed for this. The application of RBF neural network for state estimation is investigated by testing its applicability on a IEEE 14 bus ...
El-Melegy, Moumen T
2013-07-01
This paper addresses the problem of fitting a functional model to data corrupted with outliers using a multilayered feed-forward neural network. Although it is of high importance in practical applications, this problem has not received careful attention from the neural network research community. One recent approach to solving this problem is to use a neural network training algorithm based on the random sample consensus (RANSAC) framework. This paper proposes a new algorithm that offers two enhancements over the original RANSAC algorithm. The first one improves the algorithm accuracy and robustness by employing an M-estimator cost function to decide on the best estimated model from the randomly selected samples. The other one improves the time performance of the algorithm by utilizing a statistical pretest based on Wald's sequential probability ratio test. The proposed algorithm is successfully evaluated on synthetic and real data, contaminated with varying degrees of outliers, and compared with existing neural network training algorithms.
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.
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...
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.
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.
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.
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.
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.
Directory of Open Access Journals (Sweden)
Yih-Lon Lin
2013-01-01
Full Text Available If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.
Smith, Imogen; Silveirinha, Vasco; Stein, Jason L; de la Torre-Ubieta, Luis; Farrimond, Jonathan A; Williamson, Elizabeth M; Whalley, Benjamin J
2017-04-01
Differentiated human neural stem cells were cultured in an inert three-dimensional (3D) scaffold and, unlike two-dimensional (2D) but otherwise comparable monolayer cultures, formed spontaneously active, functional neuronal networks that responded reproducibly and predictably to conventional pharmacological treatments to reveal functional, glutamatergic synapses. Immunocytochemical and electron microscopy analysis revealed a neuronal and glial population, where markers of neuronal maturity were observed in the former. Oligonucleotide microarray analysis revealed substantial differences in gene expression conferred by culturing in a 3D vs a 2D environment. Notable and numerous differences were seen in genes coding for neuronal function, the extracellular matrix and cytoskeleton. In addition to producing functional networks, differentiated human neural stem cells grown in inert scaffolds offer several significant advantages over conventional 2D monolayers. These advantages include cost savings and improved physiological relevance, which make them better suited for use in the pharmacological and toxicological assays required for development of stem cell-based treatments and the reduction of animal use in medical research. Copyright © 2015 John Wiley & Sons, Ltd. Copyright © 2015 John Wiley & Sons, Ltd.
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...
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...
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
Thomas, Michael S. C.; Purser, Harry R. M.; Tomlinson, Simon; Mareschal, Denis
2012-01-01
This article presents an investigation of the relationship between lesioning and neuroimaging methods of assessing functional specialisation, using synthetic brain imaging (SBI) and lesioning of a connectionist network of past-tense formation. The model comprised two processing "routes": one was a direct route between layers of input and output…
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.
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...
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.
Directory of Open Access Journals (Sweden)
Peng Zhang
Full Text Available Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP. Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm.
Zhang, Peng; Liu, Keping; Zhao, Bo; Li, Yuanchun
2015-01-01
Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm.
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.
Directory of Open Access Journals (Sweden)
Robert J Thoma
2016-03-01
Full Text Available Functional MRI studies have identified a distributed set of brain activations to be associated with auditory verbal hallucinations (AVH. However, very little is known about how activated brain regions may be linked together into AVH-generating networks. Fifteen volunteers with schizophrenia or schizoaffective disorder pressed buttons to indicate on-set and off-set of AVH during fMRI scanning. When a general linear model (GLM was used to compare BOLD signals during periods in which subjects indicated that they were versus were not experiencing AVH (‘AVH-on’ versus ‘AVH-off’, it revealed AVH-related activity in bilateral inferior frontal and superior temporal regions; the right middle temporal gyrus; and the left insula, supramarginal gyrus, inferior parietal lobule and extra-nuclear white matter. In an effort to identify AVH-related networks, the raw data were also processed using independent component analyses (ICA. Four ICA components were spatially consistent with an a priori network framework based upon published meta-analyses of imaging correlates of AVH. Of these four components, only a network involving bilateral auditory cortices and posterior receptive language areas was significantly and positively correlated with the pattern of AVH-on versus AVH-off. The ICA also identified two additional networks (occipital-temporal and medial pre-frontal, not fully matching the meta-analysis framework, but nevertheless containing nodes reported as active in some studies of AVH. Both networks showed significant AVH-related profiles, but both were most active during AVH-off periods. Overall, the data suggest that AVH generation requires specific and selective activation of auditory cortical and posterior language regions, perhaps coupled to a release of indirect influence by occipital and medial frontal structures.
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...
Zhao, Qingbai; Zhou, Zhijin; Xu, Haibo; Chen, Shi; Xu, Fang; Fan, Wenliang; Han, Lei
2013-01-01
The key components of insight include breaking mental sets and forming the novel, task-related associations. The majority of researchers have agreed that the anterior cingulate cortex may mediate processes of breaking one’s mental set, while the exact neural correlates of forming novel associations are still debatable. In the present study, we used a paradigm of answer selection to explore brain activations of insight by using event-related functional magnetic resonance imaging during solving Chinese ‘chengyu’ (in Chinese pinyin) riddles. Based on the participant’s choice, the trials were classified into the insight and non-insight conditions. Both stimulus-locked and response-locked analyses are conducted to detect the neural activity corresponding to the early and late periods of insight solution, respectively. Our data indicate that the early period of insight solution shows more activation in the middle temporal gyrus, the middle frontal gyrus and the anterior cingulate cortex. These activities might be associated to the extensive semantic processing, as well as detecting and resolving cognitive conflicts. In contrast, the late period of insight solution produced increased activities in the hippocampus and the amygdala, possibly reflecting the forming of novel association and the concomitant “Aha” feeling. Our study supports the key role of hippocampus in forming novel associations, and indicates a dynamic neural network during insight solution. PMID:23555020
Hoffman, Paul; Morcom, Alexa M
2018-01-01
Semantic cognition is central to understanding of language and the world and, unlike many cognitive domains, is thought to show little age-related decline. We investigated age-related differences in the neural basis of this critical cognitive domain by performing an activation likelihood estimation (ALE) meta-analysis of functional neuroimaging studies comparing young and older people. On average, young people outperformed their older counterparts during semantic tasks. Overall, both age groups activated similar left-lateralised regions. However, older adults displayed less activation than young people in some elements of the typical left-hemisphere semantic network, including inferior prefrontal, posterior temporal and inferior parietal cortex. They also showed greater activation in right frontal and parietal regions, particularly those held to be involved in domain-general controlled processing, and principally when they performed more poorly than the young. Thus, semantic processing in later life is associated with a shift from semantic-specific to domain-general neural resources, consistent with the theory of neural dedifferentiation, and a performance-related reduction in prefrontal lateralisation, which may reflect a response to increased task demands. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.
Avidan, Galia; Behrmann, Marlene
2009-01-01
Summary There is growing consensus that the summed activity of multiple nodes of a distributed cortical network supports face recognition in humans, including “core” ventral occipito-temporal cortex (VOTC) regions [1-3], as well as “extended” regions outside VOTC [4, 5]. Surprisingly, many individuals with congenital prosopagnosia – a lifelong impairment in face processing [6-9] -- exhibit normal BOLD activation in the “core” VOTC regions [10] (but see [11]). Interestingly, these same individuals evince a reduction in the structural integrity of the white matter tracts connecting VOTC to anterior temporal and frontal cortices [12] which form part of the “extended” face network. These findings suggest that the profound impairment in congenital prosopagnosia may arise not from a dysfunction of the core VOTC areas per se but from a failure to propagate signals between the intact VOTC and the extended nodes of the network. Here, using the fMR adaptation paradigm with famous and unknown faces, we show that individuals with congenital prosopagnosia evince normal adaptation effects in VOTC, indicating sensitivity to facial identity, but, unlike controls, show no differential activation for familiar versus unknown faces outside VOTC, particularly in the precuneus/posterior cingulate cortex and the anterior paracingulate cortex. These results indicate that normal BOLD activation in VOTC is insufficient to subserve intact face recognition, and support the hypothesis that disrupted information propagation between VOTC and the extended face processing network underlies the functional impairment in congenital prosopagnosia. PMID:19481456
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...
Comparative performance of some popular artificial neural network ...
Indian Academy of Sciences (India)
Comparative performance of some popular artificial neural network algorithms on benchmark and function approximation problems ... dynamic range of these functions, it is suggested that these functions can also be considered as standard benchmark problems for function approximation using artificial neural networks.
Directory of Open Access Journals (Sweden)
Stefano Luccioli
2014-09-01
Full Text Available It has recently been discovered that single neuron stimulation can impact network dynamics in immature and adult neuronal circuits. Here we report a novel mechanism which can explain in neuronal circuits, at an early stage of development, the peculiar role played by a few specific neurons in promoting/arresting the population activity. For this purpose, we consider a standard neuronal network model, with short-term synaptic plasticity, whose population activity is characterized by bursting behavior. The addition of developmentally inspired constraints and correlations in the distribution of the neuronal connectivities and excitabilities leads to the emergence of functional hub neurons, whose stimulation/deletion is critical for the network activity. Functional hubs form a clique, where a precise sequential activation of the neurons is essential to ignite collective events without any need for a specific topological architecture. Unsupervised time-lagged firings of supra-threshold cells, in connection with coordinated entrainments of near-threshold neurons, are the key ingredients to orchestrate population activity.
Rai, H. M.; Trivedi, A.; Chatterjee, K.; Shukla, S.
2014-01-01
This paper employed the Daubechies wavelet transform (WT) for R-peak detection and radial basis function neural network (RBFNN) to classify the electrocardiogram (ECG) signals. Five types of ECG beats: normal beat, paced beat, left bundle branch block (LBBB) beat, right bundle branch block (RBBB) beat and premature ventricular contraction (PVC) were classified. 500 QRS complexes were arbitrarily extracted from 26 records in Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, which are available on Physionet website. Each and every QRS complex was represented by 21 points from p1 to p21 and these QRS complexes of each record were categorized according to types of beats. The system performance was computed using four types of parameter evaluation metrics: sensitivity, positive predictivity, specificity and classification error rate. The experimental result shows that the average values of sensitivity, positive predictivity, specificity and classification error rate are 99.8%, 99.60%, 99.90% and 0.12%, respectively with RBFNN classifier. The overall accuracy achieved for back propagation neural network (BPNN), multilayered perceptron (MLP), support vector machine (SVM) and RBFNN classifiers are 97.2%, 98.8%, 99% and 99.6%, respectively. The accuracy levels and processing time of RBFNN is higher than or comparable with BPNN, MLP and SVM classifiers.
Directory of Open Access Journals (Sweden)
Deliang Yu
2017-01-01
Full Text Available This paper presents a new method to diagnose oil well pump faults using a modified radial basis function neural network. With the development of submersible linear motor technology, rodless pumping units have been widely used in oil exploration. However, the ground indicator diagram method cannot be used to diagnose the working conditions of rodless pumping units because it is based on the load change of the polished rod suspension point and its displacement. To solve this problem, this paper presents a new method that is applicable to rodless oil pumps. The advantage of this new method is its use of a simple feature extraction method and advanced genetic algorithm to optimize the threshold and weight of the RBF neural network. In this paper, we extract the characteristic value from the operation parameters of the submersible linear motor and oil wellhead as the input vector of the fault diagnosis model. Through experimental analysis, the proposed method is proven to have good convergence performance, high accuracy, and high reliability.
Kumar, M; Mishra, S K
2017-01-01
The clinical magnetic resonance imaging (MRI) images may get corrupted due to the presence of the mixture of different types of noises such as Rician, Gaussian, impulse, etc. Most of the available filtering algorithms are noise specific, linear, and non-adaptive. There is a need to develop a nonlinear adaptive filter that adapts itself according to the requirement and effectively applied for suppression of mixed noise from different MRI images. In view of this, a novel nonlinear neural network based adaptive filter i.e. functional link artificial neural network (FLANN) whose weights are trained by a recently developed derivative free meta-heuristic technique i.e. teaching learning based optimization (TLBO) is proposed and implemented. The performance of the proposed filter is compared with five other adaptive filters and analyzed by considering quantitative metrics and evaluating the nonparametric statistical test. The convergence curve and computational time are also included for investigating the efficiency of the proposed as well as competitive filters. The simulation outcomes of proposed filter outperform the other adaptive filters. The proposed filter can be hybridized with other evolutionary technique and utilized for removing different noise and artifacts from others medical images more competently.
Artificial neural networks with an infinite number of nodes
Blekas, K.; Lagaris, I. E.
2017-10-01
A new class of Artificial Neural Networks is described incorporating a node density function and functional weights. This network containing an infinite number of nodes, excels in generalizing and possesses a superior extrapolation capability.
Directory of Open Access Journals (Sweden)
M.R. Mosavi
2016-01-01
Full Text Available This paper presents a new method to estimate the time of important earthquakes in Hormozgan region with magnitude greater than 5.5 based on the Radial Basis Function (RBF Neural Network (NN models. Input vector to the network is composed of different seismicity rates between main events that are calculated in convenient and reliable way to create optimized training methods. It helps network with a limited number of training data to estimation. It is common for earthquakes modeling by data-driven methods in this case. In addition, the proposed method is combined with Rosenberg cluster method to remove aftershocks events from the history of catalog for NN to better process the data. The results show that created RBF model successfully estimates the interevent times between large and sequence earthquakes that can be used as a tool to predict earthquake, so that comparison with other NN structure, for example Multi-Layer Perceptron (MLP NN, reveals the superiority of the proposed method. Because of superiority proposed method has higher accuracy, lower costs and simpler network structure.
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.
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...
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.
Hardison, Nicholas E; Fanelli, Theresa J; Dudek, Scott M; Reif, David M; Ritchie, Marylyn D; Motsinger-Reif, Alison A
2008-01-01
Grammatical Evolution Neural Networks (GENN) is a computational method designed to detect gene-gene interactions in genetic epidemiology, but has so far only been evaluated in situations with balanced numbers of cases and controls. Real data, however, rarely has such perfectly balanced classes. In the current study, we test the power of GENN to detect interactions in data with a range of class imbalance using two fitness functions (classification error and balanced error), as well as data re-sampling. We show that when using classification error, class imbalance greatly decreases the power of GENN. Re-sampling methods demonstrated improved power, but using balanced accuracy resulted in the highest power. Based on the results of this study, balanced error has replaced classification error in the GENN algorithm.
Zhou, Jingwen; Xu, Zhenghong; Chen, Shouwen
2013-04-01
The thuringiensin abiotic degradation processes in aqueous solution under different conditions, with a pH range of 5.0-9.0 and a temperature range of 10-40°C, were systematically investigated by an exponential decay model and a radius basis function (RBF) neural network model, respectively. The half-lives of thuringiensin calculated by the exponential decay model ranged from 2.72 d to 16.19 d under the different conditions mentioned above. Furthermore, an RBF model with accuracy of 0.1 and SPREAD value 5 was employed to model the degradation processes. The results showed that the model could simulate and predict the degradation processes well. Both the half-lives and the prediction data showed that thuringiensin was an easily degradable antibiotic, which could be an important factor in the evaluation of its safety. Copyright © 2012 Elsevier Ltd. All rights reserved.
One pass learning for generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2016-01-01
Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network is proposed to overcome this disadvantage. Proposed method utilizes standard deviation of each class to calculate corresponding smoothing parameter. Since different datasets may have different standard deviations and data distributions, proposed method tries to handle these differences by defining two functions for smoothing parameter calculation. Thresholding is applied to determine which function will be used. One of these functions is defined for datasets having different range of values. It provides balanced smoothing parameters for these datasets through logarithmic function and changing the operation range to lower boundary. On the other hand, the other function calculates smoothing parameter value for classes having standard deviation smaller than the threshold value. Proposed method is tested on 14 datasets and performance of one pass learning generalized classifier neural network is compared with that of probabilistic neural network, radial basis function neural network, extreme learning machines, and standard and logarithmic learning generalized classifier neural network in MATLAB environment. One pass learning generalized classifier neural network provides more than a thousand times faster classification than standard and logarithmic generalized classifier neural network. Due to its classification accuracy and speed, one pass generalized classifier neural network can be considered as an efficient alternative to probabilistic neural network. Test results show that proposed method overcomes computational drawback of generalized classifier neural network and may increase the classification performance. Copyright
The Usage of Neural Networks for the Medical Diagnosis
Malyshevska, Kateryna
2009-01-01
The problem of cancer diagnosis from multi-channel images using the neural networks is investigated. The goal of this work is to classify the different tissue types which are used to determine the cancer risk. The radial basis function networks and backpropagation neural networks are used for classification. The results of experiments are presented.
Thaut, Michael H; Peterson, David A; McIntosh, Gerald C
2005-12-01
In a series of experiments, we have begun to investigate the effect of music as a mnemonic device on learning and memory and the underlying plasticity of oscillatory neural networks. We used verbal learning and memory tests (standardized word lists, AVLT) in conjunction with electroencephalographic analysis to determine differences between verbal learning in either a spoken or musical (verbal materials as song lyrics) modality. In healthy adults, learning in both the spoken and music condition was associated with significant increases in oscillatory synchrony across all frequency bands. A significant difference between the spoken and music condition emerged in the cortical topography of the learning-related synchronization. When using EEG measures as predictors during learning for subsequent successful memory recall, significantly increased coherence (phase-locked synchronization) within and between oscillatory brain networks emerged for music in alpha and gamma bands. In a similar study with multiple sclerosis patients, superior learning and memory was shown in the music condition when controlled for word order recall, and subjects were instructed to sing back the word lists. Also, the music condition was associated with a significant power increase in the low-alpha band in bilateral frontal networks, indicating increased neuronal synchronization. Musical learning may access compensatory pathways for memory functions during compromised PFC functions associated with learning and recall. Music learning may also confer a neurophysiological advantage through the stronger synchronization of the neuronal cell assemblies underlying verbal learning and memory. Collectively our data provide evidence that melodic-rhythmic templates as temporal structures in music may drive internal rhythm formation in recurrent cortical networks involved in learning and memory.
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.
Feature to prototype transition in neural networks
Krotov, Dmitry; Hopfield, John
Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.
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.
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.
Trzepiecinski, T.; Lemu, H. G.
2017-11-01
Many technological factors affect the friction phenomenon in sheet metal forming process. As a result, the determination of the analytical model describing the frictional resistance is very difficult. In this paper, a friction model was built based on the experimental results of strip drawing tests. Friction tests were carried out in order to determine the effect of surface and tool roughness parameters, the pressure force and mechanical parameters of the sheets on the value of coefficient of friction. The strip drawing friction tests were conducted on aluminium alloy sheets: AA5251-H14, AA5754-H14, AA5754-H18, AA5754-H24. The surface topography of the sheets was measured using Taylor Hobson Surtronic 3+ instrument. In order to describe complex relations between friction and factors influencing tribological conditions of sheet metal forming, the multilayer artificial network was built in Statistica Neural Network program. The effect of activation function and post synaptic potential function on the sensitivity of multilayer neural network to predict the friction coefficient value is presented. It has been found that the difference in the prediction of error of neural network for different approaches can reach 400%. So, the proper selection of activation and post synaptic potential functions is crucial in neural network modelling.
Effects of gratitude meditation on neural network functional connectivity and brain-heart coupling.
Kyeong, Sunghyon; Kim, Joohan; Kim, Dae Jin; Kim, Hesun Erin; Kim, Jae-Jin
2017-07-11
A sense of gratitude is a powerful and positive experience that can promote a happier life, whereas resentment is associated with life dissatisfaction. To explore the effects of gratitude and resentment on mental well-being, we acquired functional magnetic resonance imaging and heart rate (HR) data before, during, and after the gratitude and resentment interventions. Functional connectivity (FC) analysis was conducted to identify the modulatory effects of gratitude on the default mode, emotion, and reward-motivation networks. The average HR was significantly lower during the gratitude intervention than during the resentment intervention. Temporostriatal FC showed a positive correlation with HR during the gratitude intervention, but not during the resentment intervention. Temporostriatal resting-state FC was significantly decreased after the gratitude intervention compared to the resentment intervention. After the gratitude intervention, resting-state FC of the amygdala with the right dorsomedial prefrontal cortex and left dorsal anterior cingulate cortex were positively correlated with anxiety scale and depression scale, respectively. Taken together, our findings shed light on the effect of gratitude meditation on an individual's mental well-being, and indicate that it may be a means of improving both emotion regulation and self-motivation by modulating resting-state FC in emotion and motivation-related brain regions.
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
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.
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.
Nie, Xiaobing; Zheng, Wei Xing; Cao, Jinde
2015-11-01
The problem of coexistence and dynamical behaviors of multiple equilibrium points is addressed for a class of memristive Cohen-Grossberg neural networks with non-monotonic piecewise linear activation functions and time-varying delays. By virtue of the fixed point theorem, nonsmooth analysis theory and other analytical tools, some sufficient conditions are established to guarantee that such n-dimensional memristive Cohen-Grossberg neural networks can have 5(n) equilibrium points, among which 3(n) equilibrium points are locally exponentially stable. It is shown that greater storage capacity can be achieved by neural networks with the non-monotonic activation functions introduced herein than the ones with Mexican-hat-type activation function. In addition, unlike most existing multistability results of neural networks with monotonic activation functions, those obtained 3(n) locally stable equilibrium points are located both in saturated regions and unsaturated regions. The theoretical findings are verified by an illustrative example with computer simulations. Copyright © 2015 Elsevier Ltd. All rights reserved.
Dominey, Peter Ford; Inui, Toshio; Hoen, Michel
2009-01-01
A central issue in cognitive neuroscience today concerns how distributed neural networks in the brain that are used in language learning and processing can be involved in non-linguistic cognitive sequence learning. This issue is informed by a wealth of functional neurophysiology studies of sentence comprehension, along with a number of recent…
Based on BP Neural Network Stock Prediction
Liu, Xiangwei; Ma, Xin
2012-01-01
The stock market has a high profit and high risk features, on the stock market analysis and prediction research has been paid attention to by people. Stock price trend is a complex nonlinear function, so the price has certain predictability. This article mainly with improved BP neural network (BPNN) to set up the stock market prediction model, and…
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.
Feedforward Backpropagation Neural Networks in Prediction of Farmer Risk Preferences
Kastens, Terry L.; Featherstone, Allen M.
1996-01-01
An out-of-sample prediction of Kansas farmers' responses to five surveyed questions involving risk is used to compare ordered multinomial logistic regression models with feedforward backpropagation neural network models. Although the logistic models often predict more accurately than the neural network models in a mean-squared error sense, the neural network models are shown to be more accommodating of loss functions associated with a desire to predict certain combinations of categorical resp...
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.
Computational capabilities of graph neural networks.
Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele
2009-01-01
In this paper, we will consider the approximation properties of a recently introduced neural network model called graph neural network (GNN), which can be used to process-structured data inputs, e.g., acyclic graphs, cyclic graphs, and directed or undirected graphs. This class of neural networks implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n onto an m-dimensional Euclidean space. We characterize the functions that can be approximated by GNNs, in probability, up to any prescribed degree of precision. This set contains the maps that satisfy a property called preservation of the unfolding equivalence, and includes most of the practically useful functions on graphs; the only known exception is when the input graph contains particular patterns of symmetries when unfolding equivalence may not be preserved. The result can be considered an extension of the universal approximation property established for the classic feedforward neural networks (FNNs). Some experimental examples are used to show the computational capabilities of the proposed model.
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.
Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship
Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.
2010-01-01
The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…
Panagou, Efstathios Z
2008-04-01
A radial basis function neural network was developed to determine the kinetic behavior of Listeria monocytogenes in Katiki, a traditional white acid-curd soft spreadable cheese. The applicability of the neural network approach was compared with the reparameterized Gompertz, the modified Weibull, and the Geeraerd primary models. Model performance was assessed with the root mean square error of the residuals of the model (RMSE), the regression coefficient (R2), and the F test. Commercially prepared cheese samples were artificially inoculated with a five-strain cocktail of L. monocytogenes, with an initial concentration of 10(6) CFU g(-1) and stored at 5, 10, 15, and 20 degrees C for 40 days. At each storage temperature, a pathogen viability loss profile was evident and included a shoulder, a log-linear phase, and a tailing phase. The developed neural network described the survival of L. monocytogenes equally well or slightly better than did the three primary models. The performance indices for the training subset of the network were R2 = 0.993 and RMSE = 0.214. The relevant mean values for all storage temperatures were R2 = 0.981, 0.986, and 0.985 and RMSE = 0.344, 0.256, and 0.262 for the reparameterized Gompertz, modified Weibull, and Geeraerd models, respectively. The results of the F test indicated that none of the primary models were able to describe accurately the survival of the pathogen at 5 degrees C, whereas with the neural network all fvalues were significant. The neural network and primary models all were validated under constant temperature storage conditions (12 and 17 degrees C). First or second order polynomial models were used to relate the inactivation parameters to temperature, whereas the neural network was used a one-step modeling approach. Comparison of the prediction capability was based on bias and accuracy factors and on the goodness-of-fit index. The prediction performance of the neural network approach was equal to that of the primary
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...
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
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Morawietz, Tobias; Behler, Jörg
2013-08-15
The fundamental importance of water for many chemical processes has motivated the development of countless efficient but approximate water potentials for large-scale molecular dynamics simulations, from simple empirical force fields to very sophisticated flexible water models. Accurate and generally applicable water potentials should fulfill a number of requirements. They should have a quality close to quantum chemical methods, they should explicitly depend on all degrees of freedom including all relevant many-body interactions, and they should be able to describe molecular dissociation and recombination. In this work, we present a high-dimensional neural network (NN) potential for water clusters based on density-functional theory (DFT) calculations, which is constructed using clusters containing up to 10 monomers and is in principle able to meet all these requirements. We investigate the reliability of specific parametrizations employing two frequently used generalized gradient approximation (GGA) exchange-correlation functionals, PBE and RPBE, as reference methods. We find that the binding energy errors of the NN potentials with respect to DFT are significantly lower than the typical uncertainties of DFT calculations arising from the choice of the exchange-correlation functional. Further, we examine the role of van der Waals interactions, which are not properly described by GGA functionals. Specifically, we incorporate the D3 scheme suggested by Grimme (J. Chem. Phys. 2010, 132, 154104) in our potentials and demonstrate that it can be applied to GGA-based NN potentials in the same way as to DFT calculations without modification. Our results show that the description of small water clusters provided by the RPBE functional is significantly improved if van der Waals interactions are included, while in case of the PBE functional, which is well-known to yield stronger binding than RPBE, van der Waals corrections lead to overestimated binding energies.
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...
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 ...
A hardware implementation of neural network with modified HANNIBAL architecture
Energy Technology Data Exchange (ETDEWEB)
Lee, Bum youb; Chung, Duck Jin [Inha University, Inchon (Korea, Republic of)
1996-03-01
A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). 14 refs., 10 figs., 3 tabs.
Yang, Yanchao; Jiang, Hong; Liu, Congbin; Lan, Zhongli
2013-03-01
Cognitive radio (CR) is an intelligent wireless communication system which can dynamically adjust the parameters to improve system performance depending on the environmental change and quality of service. The core technology for CR is the design of cognitive engine, which introduces reasoning and learning methods in the field of artificial intelligence, to achieve the perception, adaptation and learning capability. Considering the dynamical wireless environment and demands, this paper proposes a design of cognitive engine based on the rough sets (RS) and radial basis function neural network (RBF_NN). The method uses experienced knowledge and environment information processed by RS module to train the RBF_NN, and then the learning model is used to reconfigure communication parameters to allocate resources rationally and improve system performance. After training learning model, the performance is evaluated according to two benchmark functions. The simulation results demonstrate the effectiveness of the model and the proposed cognitive engine can effectively achieve the goal of learning and reconfiguration in cognitive radio.
Sbarufatti, Claudio; Corbetta, Matteo; Giglio, Marco; Cadini, Francesco
2017-03-01
Lithium-Ion rechargeable batteries are widespread power sources with applications to consumer electronics, electrical vehicles, unmanned aerial and spatial vehicles, etc. The failure to supply the required power levels may lead to severe safety and economical consequences. Thus, in view of the implementation of adequate maintenance strategies, the development of diagnostic and prognostic tools for monitoring the state of health of the batteries and predicting their remaining useful life is becoming a crucial task. Here, we propose a method for predicting the end of discharge of Li-Ion batteries, which stems from the combination of particle filters with radial basis function neural networks. The major innovation lies in the fact that the radial basis function model is adaptively trained on-line, i.e., its parameters are identified in real time by the particle filter as new observations of the battery terminal voltage become available. By doing so, the prognostic algorithm achieves the flexibility needed to provide sound end-of-discharge time predictions as the charge-discharge cycles progress, even in presence of anomalous behaviors due to failures or unforeseen operating conditions. The method is demonstrated with reference to actual Li-Ion battery discharge data contained in the prognostics data repository of the NASA Ames Research Center database.
A Topological Perspective of Neural Network Structure
Sizemore, Ann; Giusti, Chad; Cieslak, Matthew; Grafton, Scott; Bassett, Danielle
The wiring patterns of white matter tracts between brain regions inform functional capabilities of the neural network. Indeed, densely connected and cyclically arranged cognitive systems may communicate and thus perform distinctly. However, previously employed graph theoretical statistics are local in nature and thus insensitive to such global structure. Here we present an investigation of the structural neural network in eight healthy individuals using persistent homology. An extension of homology to weighted networks, persistent homology records both circuits and cliques (all-to-all connected subgraphs) through a repetitive thresholding process, thus perceiving structural motifs. We report structural features found across patients and discuss brain regions responsible for these patterns, finally considering the implications of such motifs in relation to cognitive function.
Dewhurst, Henry M; Torres, Matthew P
2017-01-01
Post-translational modifications (PTMs) provide an extensible framework for regulation of protein behavior beyond the diversity represented within the genome alone. While the rate of identification of PTMs has rapidly increased in recent years, our knowledge of PTM functionality encompasses less than 5% of this data. We previously developed SAPH-ire (Structural Analysis of PTM Hotspots) for the prioritization of eukaryotic PTMs based on function potential of discrete modified alignment positions (MAPs) in a set of 8 protein families. A proteome-wide expansion of the dataset to all families of PTM-bearing, eukaryotic proteins with a representational crystal structure and the application of artificial neural network (ANN) models demonstrated the broader applicability of this approach. Although structural features of proteins have been repeatedly demonstrated to be predictive of PTM functionality, the availability of adequately resolved 3D structures in the Protein Data Bank (PDB) limits the scope of these methods. In order to bridge this gap and capture the larger set of PTM-bearing proteins without an available, homologous structure, we explored all available MAP features as ANN inputs to identify predictive models that do not rely on 3D protein structural data. This systematic, algorithmic approach explores 8 available input features in exhaustive combinations (247 models; size 2-8). To control for potential bias in random sampling for holdback in training sets, we iterated each model across 100 randomized, sample training and testing sets-yielding 24,700 individual ANNs. The size of the analyzed dataset and iterative generation of ANNs represents the largest and most thorough investigation of predictive models for PTM functionality to date. Comparison of input layer combinations allows us to quantify ANN performance with a high degree of confidence and subsequently select a top-ranked, robust fit model which highlights 3,687 MAPs, including 10,933 PTMs with a high
Ardell, Jeffrey L; Rajendran, Pradeep S; Nier, Heath A; KenKnight, Bruce H; Armour, J Andrew
2015-11-15
Using vagus nerve stimulation (VNS), we sought to determine the contribution of vagal afferents to efferent control of cardiac function. In anesthetized dogs, the right and left cervical vagosympathetic trunks were stimulated in the intact state, following ipsilateral or contralateral vagus nerve transection (VNTx), and then following bilateral VNTx. Stimulations were performed at currents from 0.25 to 4.0 mA, frequencies from 2 to 30 Hz, and a 500-μs pulse width. Right or left VNS evoked significantly greater current- and frequency-dependent suppression of chronotropic, inotropic, and lusitropic function subsequent to sequential VNTx. Bradycardia threshold was defined as the current first required for a 5% decrease in heart rate. The threshold for the right vs. left vagus-induced bradycardia in the intact state (2.91 ± 0.18 and 3.47 ± 0.20 mA, respectively) decreased significantly with right VNTx (1.69 ± 0.17 mA for right and 3.04 ± 0.27 mA for left) and decreased further following bilateral VNTx (1.29 ± 0.16 mA for right and 1.74 ± 0.19 mA for left). Similar effects were observed following left VNTx. The thresholds for afferent-mediated effects on cardiac parameters were 0.62 ± 0.04 and 0.65 ± 0.06 mA with right and left VNS, respectively, and were reflected primarily as augmentation. Afferent-mediated tachycardias were maintained following β-blockade but were eliminated by VNTx. The increased effectiveness and decrease in bradycardia threshold with sequential VNTx suggest that 1) vagal afferents inhibit centrally mediated parasympathetic efferent outflow and 2) the ipsilateral and contralateral vagi exert a substantial buffering capacity. The intact threshold reflects the interaction between multiple levels of the cardiac neural hierarchy. Copyright © 2015 the American Physiological Society.
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....
Artificial neural networks in predicting current in electric arc furnaces
Panoiu, M.; Panoiu, C.; Iordan, A.; Ghiormez, L.
2014-03-01
The paper presents a study of the possibility of using artificial neural networks for the prediction of the current and the voltage of Electric Arc Furnaces. Multi-layer perceptron and radial based functions Artificial Neural Networks implemented in Matlab were used. The study is based on measured data items from an Electric Arc Furnace in an industrial plant in Romania.
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
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.
DEFF Research Database (Denmark)
Madsen, Per Printz
1999-01-01
The purpose of this paper is to describe a neural network (SNN), that is based on Shannons ideas of reconstruction of a real continuous function from its samples. The basic function, used in this network, is the Sinc-function. Two learning algorithms are described. A simple one called IM...
DEFF Research Database (Denmark)
Madsen, Per Printz
1998-01-01
The purpose of this paper is to describe a neural network (SNN), that is based on Shannons ideas of reconstruction of a real continuous function from its samples. The basic function, used in this network, is the Sinc-function. Two learning algorithms are described. A simple one called IM...
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.
Nguyen, Hieu T T; Le, Hung M
2012-05-10
The classical interchange (permutation) of atoms of similar identity does not have an effect on the overall potential energy. In this study, we present feed-forward neural network structures that provide permutation symmetry to the potential energy surfaces of molecules. The new feed-forward neural network structures are employed to fit the potential energy surfaces for two illustrative molecules, which are H(2)O and ClOOCl. Modifications are made to describe the symmetric interchange (permutation) of atoms of similar identity (or mathematically, the permutation of symmetric input parameters). The combined-function-derivative approximation algorithm (J. Chem. Phys. 2009, 130, 134101) is also implemented to fit the neural-network potential energy surfaces accurately. The combination of our symmetric neural networks and the function-derivative fitting effectively produces PES fits using fewer numbers of training data points. For H(2)O, only 282 configurations are employed as the training set; the testing root-mean-squared and mean-absolute energy errors are respectively reported as 0.0103 eV (0.236 kcal/mol) and 0.0078 eV (0.179 kcal/mol). In the ClOOCl case, 1693 configurations are required to construct the training set; the root-mean-squared and mean-absolute energy errors for the ClOOCl testing set are 0.0409 eV (0.943 kcal/mol) and 0.0269 eV (0.620 kcal/mol), respectively. Overall, we find good agreements between ab initio and NN prediction in term of energy and gradient errors, and conclude that the new feed-forward neural-network models advantageously describe the molecules with excellent accuracy.
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
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...
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 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
Neural modeling of prefrontal executive function
Energy Technology Data Exchange (ETDEWEB)
Levine, D.S. [Univ. of Texas, Arlington, TX (United States)
1996-12-31
Brain executive function is based in a distributed system whereby prefrontal cortex is interconnected with other cortical. and subcortical loci. Executive function is divided roughly into three interacting parts: affective guidance of responses; linkage among working memory representations; and forming complex behavioral schemata. Neural network models of each of these parts are reviewed and fit into a preliminary theoretical framework.
Hybrid discrete-time neural networks.
Cao, Hongjun; Ibarz, Borja
2010-11-13
Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast-slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.
Artificial Neural Network for Displacement Vectors Determination
Directory of Open Access Journals (Sweden)
P. Bohmann
1997-09-01
Full Text Available An artificial neural network (NN for displacement vectors (DV determination is presented in this paper. DV are computed in areas which are essential for image analysis and computer vision, in areas where are edges, lines, corners etc. These special features are found by edges operators with the following filtration. The filtration is performed by a threshold function. The next step is DV computation by 2D Hamming artificial neural network. A method of DV computation is based on the full search block matching algorithms. The pre-processing (edges finding is the reason why the correlation function is very simple, the process of DV determination needs less computation and the structure of the NN is simpler.
Tumor Diagnosis Using Backpropagation Neural Network Method
Ma, Lixing; Looney, Carl; Sukuta, Sydney; Bruch, Reinhard; Afanasyeva, Natalia
1998-05-01
For characterization of skin cancer, an artificial neural network (ANN) method has been developed to diagnose normal tissue, benign tumor and melanoma. The pattern recognition is based on a three-layer neural network fuzzy learning system. In this study, the input neuron data set is the Fourier Transform infrared (FT-IR)spectrum obtained by a new Fiberoptic Evanescent Wave Fourier Transform Infrared (FEW-FTIR) spectroscopy method in the range of 1480 to 1850 cm-1. Ten input features are extracted from the absorbency values in this region. A single hidden layer of neural nodes with sigmoids activation functions clusters the feature space into small subclasses and the output nodes are separated in different nonconvex classes to permit nonlinear discrimination of disease states. The output is classified as three classes: normal tissue, benign tumor and melanoma. The results obtained from the neural network pattern recognition are shown to be consistent with traditional medical diagnosis. Input features have also been extracted from the absorbency spectra using chemical factor analysis. These abstract features or factors are also used in the classification.
Altered Synchronizations among Neural Networks in Geriatric Depression.
Wang, Lihong; Chou, Ying-Hui; Potter, Guy G; Steffens, David C
2015-01-01
Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression.
Srinivasa, Narayan; Jiang, Qin
2013-01-01
This study describes a spiking model that self-organizes for stable formation and maintenance of orientation and ocular dominance maps in the visual cortex (V1). This self-organization process simulates three development phases: an early experience-independent phase, a late experience-independent phase and a subsequent refinement phase during which experience acts to shape the map properties. The ocular dominance maps that emerge accommodate the two sets of monocular inputs that arise from the lateral geniculate nucleus (LGN) to layer 4 of V1. The orientation selectivity maps that emerge feature well-developed iso-orientation domains and fractures. During the last two phases of development the orientation preferences at some locations appear to rotate continuously through ±180° along circular paths and referred to as pinwheel-like patterns but without any corresponding point discontinuities in the orientation gradient maps. The formation of these functional maps is driven by balanced excitatory and inhibitory currents that are established via synaptic plasticity based on spike timing for both excitatory and inhibitory synapses. The stability and maintenance of the formed maps with continuous synaptic plasticity is enabled by homeostasis caused by inhibitory plasticity. However, a prolonged exposure to repeated stimuli does alter the formed maps over time due to plasticity. The results from this study suggest that continuous synaptic plasticity in both excitatory neurons and interneurons could play a critical role in the formation, stability, and maintenance of functional maps in the cortex.
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
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.
A Novel Neural Network for Generally Constrained Variational Inequalities.
Gao, Xingbao; Liao, Li-Zhi
2017-09-01
This paper presents a novel neural network for solving generally constrained variational inequality problems by constructing a system of double projection equations. By defining proper convex energy functions, the proposed neural network is proved to be stable in the sense of Lyapunov and converges to an exact solution of the original problem for any starting point under the weaker cocoercivity condition or the monotonicity condition of the gradient mapping on the linear equation set. Furthermore, two sufficient conditions are provided to ensure the stability of the proposed neural network for a special case. The proposed model overcomes some shortcomings of existing continuous-time neural networks for constrained variational inequality, and its stability only requires some monotonicity conditions of the underlying mapping and the concavity of nonlinear inequality constraints on the equation set. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
Neural network simulation of the industrial producer price index dynamical series
Soshnikov, L. E.
2013-01-01
This paper is devoted the simulation and forecast of dynamical series of the economical indicators. Multilayer perceptron and Radial basis function neural networks have been used. The neural networks model results are compared with the econometrical modeling.
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.
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.
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.
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.
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 ...
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.
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.
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.
Reeves, P.; McKenna, S. A.; Takeuchi, S.; Saegusa, H.
2003-12-01
In situ measurements of hydraulic conductivity in fractured rocks are expensive to acquire. Borehole geophysical measurements are relatively inexpensive to acquire but do not provide direct information on hydraulic conductivity. These geophysical measurements quantify properties of the rock that influence the hydraulic conductivity and it may be possible to employ a non-linear combination of these measurements to estimate hydraulic conductivity. Geophysical measurements collected in fractured granite at the Shobasama site in central Japan were used as the input to a feed-forward neural network. A simple genetic algorithm was used to simultaneously evolve the architecture and parameters of the neural network as well as determine an optimal subset of geophysical measurements for the prediction of hydraulic conductivity. The initial estimation procedure focused on predicting the class of the hydraulic conductivity, high, medium or low, from the geophysical measurements. This estimation was done while using the genetic algorithm to simultaneously determine the most important geophysical logs and optimize the architecture of the neural network. Results show that certain geophysical logs provide more information than others- most notably the short-normal resistivity, micro-resistivity, porosity and sonic logs provided the most information on hydraulic conductivity. The neural network produced excellent training results with accuracy of 90 percent or greater, but was unable to produce accurate predictions of the hydraulic conductivity class In the second phase of calculations, the selection of geophysical measurements is limited to only those that provide significant information. Additionally, this second phase predicts transmissivity instead of hydraulic conductivity in order to account for the differences in the length of the hydraulic test zones. Resulting predictions of transmissivity exhibit conditional bias with maximum prediction errors of three orders of magnitude
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.
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
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.
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.
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...
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.
The Laplacian spectrum of neural networks
de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.
2014-01-01
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286
Neural 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...
Neural Network Approach to Locating Cryptography in Object Code
Energy Technology Data Exchange (ETDEWEB)
Jason L. Wright; Milos Manic
2009-09-01
Finding and identifying cryptography is a growing concern in the malware analysis community. In this paper, artificial neural networks are used to classify functional blocks from a disassembled program as being either cryptography related or not. The resulting system, referred to as NNLC (Neural Net for Locating Cryptography) is presented and results of applying this system to various libraries are described.
Research on the Application of Artificial Neural Networks in Tender Offer for Construction Projects
Minli, Zhang; Shanshan, Qiao
The BP model in artificial neural network is used in this paper. Various factors that affect the tender offer is identified and these factors as the input nodes of network to conduct iterated operation in the network is applied in this paper. Through taking advantage of the self-learning function of network, this paper constantly modifies the weight matrix to achieve the objective error of the network error to achieve the function of predicting offer. As a software support tool, MATLAB is used in artificial neural network, the neural network toolbox helps to reduce the workload of writing code greatly and make the application of neural network more widely.
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.
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.
Application of artificial neural networks (ANNs) in wine technology.
Baykal, Halil; Yildirim, Hatice Kalkan
2013-01-01
In recent years, neural networks have turned out as a powerful method for numerous practical applications in a wide variety of disciplines. In more practical terms neural networks are one of nonlinear statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data. In food technology artificial neural networks (ANNs) are useful for food safety and quality analyses, predicting chemical, functional and sensory properties of various food products during processing and distribution. In wine technology, ANNs have been used for classification and for predicting wine process conditions. This review discusses the basic ANNs technology and its possible applications in wine technology.
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.
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.
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.
Neural Networks for Non-linear Control
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....
Application of Neural Networks for Energy Reconstruction
Damgov, Jordan
2002-01-01
The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.
Neural 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
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.
Subgradient-based neural networks for nonsmooth nonconvex optimization problems.
Bian, Wei; Xue, Xiaoping
2009-06-01
This paper presents a subgradient-based neural network to solve a nonsmooth nonconvex optimization problem with a nonsmooth nonconvex objective function, a class of affine equality constraints, and a class of nonsmooth convex inequality constraints. The proposed neural network is modeled with a differential inclusion. Under a suitable assumption on the constraint set and a proper assumption on the objective function, it is proved that for a sufficiently large penalty parameter, there exists a unique global solution to the neural network and the trajectory of the network can reach the feasible region in finite time and stay there thereafter. It is proved that the trajectory of the neural network converges to the set which consists of the equilibrium points of the neural network, and coincides with the set which consists of the critical points of the objective function in the feasible region. A condition is given to ensure the convergence to the equilibrium point set in finite time. Moreover, under suitable assumptions, the coincidence between the solution to the differential inclusion and the "slow solution" of it is also proved. Furthermore, three typical examples are given to present the effectiveness of the theoretic results obtained in this paper and the good performance of the proposed neural network.
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...
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...
ARTIFICIAL NEURAL NETWORK FOR MODELS OF HUMAN OPERATOR
Directory of Open Access Journals (Sweden)
Martin Ruzek
2017-12-01
Full Text Available This paper presents a new approach to mental functions modeling with the use of artificial neural networks. The artificial neural networks seems to be a promising method for the modeling of a human operator because the architecture of the ANN is directly inspired by the biological neuron. On the other hand, the classical paradigms of artificial neural networks are not suitable because they simplify too much the real processes in biological neural network. The search for a compromise between the complexity of biological neural network and the practical feasibility of the artificial network led to a new learning algorithm. This algorithm is based on the classical multilayered neural network; however, the learning rule is different. The neurons are updating their parameters in a way that is similar to real biological processes. The basic idea is that the neurons are competing for resources and the criterion to decide which neuron will survive is the usefulness of the neuron to the whole neural network. The neuron is not using "teacher" or any kind of superior system, the neuron receives only the information that is present in the biological system. The learning process can be seen as searching of some equilibrium point that is equal to a state with maximal importance of the neuron for the neural network. This position can change if the environment changes. The name of this type of learning, the homeostatic artificial neural network, originates from this idea, as it is similar to the process of homeostasis known in any living cell. The simulation results suggest that this type of learning can be useful also in other tasks of artificial learning and recognition.
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.
Learning of N-layers neural network
Directory of Open Access Journals (Sweden)
Vladimír Konečný
2005-01-01
Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.
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
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.
Ghasemi, Nahid; Aghayari, Reza; Maddah, Heydar
2017-12-01
The present study aims at predicting and optimizing exergetic efficiency of TiO2-Al2O3/water nanofluid at different Reynolds numbers, volume fractions and twisted ratios using Artificial Neural Networks (ANN) and experimental data. Central Composite Design (CCD) and cascade Radial Basis Function (RBF) were used to display the significant levels of the analyzed factors on the exergetic efficiency. The size of TiO2-Al2O3/water nanocomposite was 20-70 nm. The parameters of ANN model were adapted by a training algorithm of radial basis function (RBF) with a wide range of experimental data set. Total mean square error and correlation coefficient were used to evaluate the results which the best result was obtained from double layer perceptron neural network with 30 neurons in which total Mean Square Error(MSE) and correlation coefficient (R2) were equal to 0.002 and 0.999, respectively. This indicated successful prediction of the network. Moreover, the proposed equation for predicting exergetic efficiency was extremely successful. According to the optimal curves, the optimum designing parameters of double pipe heat exchanger with inner twisted tape and nanofluid under the constrains of exergetic efficiency 0.937 are found to be Reynolds number 2500, twisted ratio 2.5 and volume fraction(v/v%) 0.05.
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.
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.
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
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.
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.
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.
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.
Cisler, J M; James, G A; Tripathi, S; Mletzko, T; Heim, C; Hu, X P; Mayberg, H S; Nemeroff, C B; Kilts, C D
2013-03-01
Early life stress (ELS) is a significant risk factor for depression. The effects of ELS exposure on neural network organization have not been differentiated from the effect of depression. Furthermore, many individuals exposed to ELS do not develop depression, yet the network organization patterns differentiating resiliency versus susceptibility to the depressogenic effects of ELS are not clear. Women aged 18-44 years with either a history of ELS and no history of depression (n = 7), a history of ELS and current or past depression (n = 19), or a history of neither ELS nor depression (n = 12) underwent a resting-state 3-T functional magnetic resonance imaging (fMRI) scan. An emotion regulation brain network consisting of 21 nodes was described using graph analyses and compared between groups. Group differences in network topology involved decreased global connectivity and hub-like properties for the right ventrolateral prefrontal cortex (vlPFC) and decreased local network connectivity for the dorsal anterior cingulate cortex (dACC) among resilient individuals. Decreased local connectivity and increased hub-like properties of the left amygdala, decreased hub-like properties of the dACC and decreased local connectivity of the left vlPFC were observed among susceptible individuals. Regression analyses suggested that the severity of ELS (measured by self-report) correlated negatively with global connectivity and hub-like qualities for the left dorsolateral PFC (dlPFC). These preliminary results suggest functional neural connectivity patterns specific to ELS exposure and resiliency versus susceptibility to the depressogenic effects of ELS exposure.
On the classification enhancement of radial basis function networks
Ciftcioglu, O.; Durmisevic, S.; Sariyildiz, I.S.
2001-01-01
Artificial neural networks are powerfultools for analysing information expressed as data sets, which contain complex nonlinear relationships to be identified and classified. In particular radial basis function (RBF) neural networks have outstanding features for this. However, due to far reaching
Parameterizing Stellar Spectra Using Deep Neural Networks
Li, Xiang-Ru; Pan, Ru-Yang; Duan, Fu-Qing
2017-03-01
Large-scale sky surveys are observing massive amounts of stellar spectra. The large number of stellar spectra makes it necessary to automatically parameterize spectral data, which in turn helps in statistically exploring properties related to the atmospheric parameters. This work focuses on designing an automatic scheme to estimate effective temperature ({T}{eff}), surface gravity ({log}g) and metallicity [Fe/H] from stellar spectra. A scheme based on three deep neural networks (DNNs) is proposed. This scheme consists of the following three procedures: first, the configuration of a DNN is initialized using a series of autoencoder neural networks; second, the DNN is fine-tuned using a gradient descent scheme; third, three atmospheric parameters {T}{eff}, {log}g and [Fe/H] are estimated using the computed DNNs. The constructed DNN is a neural network with six layers (one input layer, one output layer and four hidden layers), for which the number of nodes in the six layers are 3821, 1000, 500, 100, 30 and 1, respectively. This proposed scheme was tested on both real spectra and theoretical spectra from Kurucz’s new opacity distribution function models. Test errors are measured with mean absolute errors (MAEs). The errors on real spectra from the Sloan Digital Sky Survey (SDSS) are 0.1477, 0.0048 and 0.1129 dex for {log}g, {log}{T}{eff} and [Fe/H] (64.85 K for {T}{eff}), respectively. Regarding theoretical spectra from Kurucz’s new opacity distribution function models, the MAE of the test errors are 0.0182, 0.0011 and 0.0112 dex for {log}g, {log}{T}{eff} and [Fe/H] (14.90 K for {T}{eff}), respectively.
BOUNDARY DEPTH INFORMATION USING HOPFIELD NEURAL NETWORK
Directory of Open Access Journals (Sweden)
S. Xu
2016-06-01
Full Text Available Depth information is widely used for representation, reconstruction and modeling of 3D scene. Generally two kinds of methods can obtain the depth information. One is to use the distance cues from the depth camera, but the results heavily depend on the device, and the accuracy is degraded greatly when the distance from the object is increased. The other one uses the binocular cues from the matching to obtain the depth information. It is more and more mature and convenient to collect the depth information of different scenes by stereo matching methods. In the objective function, the data term is to ensure that the difference between the matched pixels is small, and the smoothness term is to smooth the neighbors with different disparities. Nonetheless, the smoothness term blurs the boundary depth information of the object which becomes the bottleneck of the stereo matching. This paper proposes a novel energy function for the boundary to keep the discontinuities and uses the Hopfield neural network to solve the optimization. We first extract the region of interest areas which are the boundary pixels in original images. Then, we develop the boundary energy function to calculate the matching cost. At last, we solve the optimization globally by the Hopfield neural network. The Middlebury stereo benchmark is used to test the proposed method, and results show that our boundary depth information is more accurate than other state-of-the-art methods and can be used to optimize the results of other stereo matching methods.
Li, Rui; Chen, Kewei; Fleisher, Adam S; Reiman, Eric M; Yao, Li; Wu, Xia
2011-06-01
This study examined the large-scale connectivity among multiple resting-state networks (RSNs) in the human brain. Independent component analysis was first applied to the resting-state functional MRI (fMRI) data acquired from 12 healthy young subjects for the separation of RSNs. Four sensory (lateral and medial visual, auditory, and sensory-motor) RSNs and four cognitive (default-mode, self-referential, dorsal and ventral attention) RSNs were identified. Gaussian Bayesian network (BN) learning approach was then used for the examination of the conditional dependencies among these RSNs and the construction of the network-to-network directional connectivity patterns. The BN based results demonstrated that sensory networks and cognitive networks were hierarchically organized. Specially, we found the sensory networks were highly intra-dependent and the cognitive networks were strongly intra-influenced. In addition, the results depicted dominant bottom-up connectivity from sensory networks to cognitive networks in which the self-referential and the default-mode networks might play respectively important roles in the process of resting-state information transfer and integration. The present study characterized the global connectivity relations among RSNs and delineated more characteristics of spontaneous activity dynamics. Copyright © 2011 Elsevier Inc. All rights reserved.
QSAR modelling using combined simple competitive learning networks and RBF neural networks.
Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E
2018-04-01
The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.
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.
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.
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 ...
Coherency and connectivity in oscillating neural networks: linear partialization analysis
Kalitzin, S.; van Dijk, B. W.; Spekreijse, H.; van Leeuwen, W. A.
1997-01-01
This paper studies the relation between the functional synaptic connections between two artificial neural networks and the correlation of their spiking activities. The model neurons had realistic non-oscillatory dynamic properties and the networks showed oscillatory behavior as a result of their
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...
Stacked Heterogeneous Neural Networks for Time Series Forecasting
Directory of Open Access Journals (Sweden)
Florin Leon
2010-01-01
Full Text Available A hybrid model for time series forecasting is proposed. It is a stacked neural network, containing one normal multilayer perceptron with bipolar sigmoid activation functions, and the other with an exponential activation function in the output layer. As shown by the case studies, the proposed stacked hybrid neural model performs well on a variety of benchmark time series. The combination of weights of the two stack components that leads to optimal performance is also studied.
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...
On limited fan-in optimal neural networks
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.; Makaruk, H.E. [Los Alamos National Lab., NM (United States); Draghici, S. [Wayne State Univ., Detroit, MI (United States). Vision and Neural Networks Lab.
1998-03-01
Because VLSI implementations do not cope well with highly interconnected nets the area of a chip growing as the cube of the fan-in--this paper analyses the influence of limited fan in on the size and VLSI optimality of such nets. Two different approaches will show that VLSI- and size-optimal discrete neural networks can be obtained for small (i.e. lower than linear) fan-in values. They have applications to hardware implementations of neural networks. The first approach is based on implementing a certain sub class of Boolean functions, IF{sub n,m} functions. The authors will show that this class of functions can be implemented in VLSI optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan ins. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on neural networks with fan-ins limited to 2. They generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan in values, while relative minimum size solutions can be obtained for fan-ins strictly lower than linear. Finally, a size-optimal neural network having small constant fan-ins will be suggested for IF{sub n,m} functions.
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.
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.
[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...
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...
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.
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.
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...
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.
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...
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 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 new one-layer neural network for linear and quadratic programming.
Gao, Xingbao; Liao, Li-Zhi
2010-06-01
In this paper, we present a new neural network for solving linear and quadratic programming problems in real time by introducing some new vectors. The proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem when the objective function is convex on the set defined by equality constraints. Compared with existing one-layer neural networks for quadratic programming problems, the proposed neural network has the least neurons and requires weak stability conditions. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
Multiple neural network approaches to clinical expert systems
Stubbs, Derek F.
1990-08-01
We briefly review the concept of computer aided medical diagnosis and more extensively review the the existing literature on neural network applications in the field. Neural networks can function as simple expert systems for diagnosis or prognosis. Using a public database we develop a neural network for the diagnosis of a major presenting symptom while discussing the development process and possible approaches. MEDICAL EXPERTS SYSTEMS COMPUTER AIDED DIAGNOSIS Biomedicine is an incredibly diverse and multidisciplinary field and it is not surprising that neural networks with their many applications are finding more and more applications in the highly non-linear field of biomedicine. I want to concentrate on neural networks as medical expert systems for clinical diagnosis or prognosis. Expert Systems started out as a set of computerized " ifthen" rules. Everything was reduced to boolean logic and the promised land of computer experts was said to be in sight. It never came. Why? First the computer code explodes as the number of " ifs" increases. All the " ifs" have to interact. Second experts are not very good at reducing expertise to language. It turns out that experts recognize patterns and have non-verbal left-brain intuition decision processes. Third learning by example rather than learning by rule is the way natural brains works and making computers work by rule-learning is hideously labor intensive. Neural networks can learn from example. They learn the results
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
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.
Wang, L. M.
2017-09-01
A novel model-free adaptive sliding mode strategy is proposed for a generalized projective synchronization (GPS) between two entirely unknown fractional-order chaotic systems subject to the external disturbances. To solve the difficulties from the little knowledge about the master-slave system and to overcome the bad effects of the external disturbances on the generalized projective synchronization, the radial basis function neural networks are used to approach the packaged unknown master system and the packaged unknown slave system (including the external disturbances). Consequently, based on the slide mode technology and the neural network theory, a model-free adaptive sliding mode controller is designed to guarantee asymptotic stability of the generalized projective synchronization error. The main contribution of this paper is that a control strategy is provided for the generalized projective synchronization between two entirely unknown fractional-order chaotic systems subject to the unknown external disturbances, and the proposed control strategy only requires that the master system has the same fractional orders as the slave system. Moreover, the proposed method allows us to achieve all kinds of generalized projective chaos synchronizations by turning the user-defined parameters onto the desired values. Simulation results show the effectiveness of the proposed method and the robustness of the controlled system.
Adaptive Neurotechnology for Making Neural Circuits Functional .
Jung, Ranu
2008-03-01
Two of the most important trends in recent technological developments are that technology is increasingly integrated with biological systems and that it is increasingly adaptive in its capabilities. Neuroprosthetic systems that provide lost sensorimotor function after a neural disability offer a platform to investigate this interplay between biological and engineered systems. Adaptive neurotechnology (hardware and software) could be designed to be biomimetic, guided by the physical and programmatic constraints observed in biological systems, and allow for real-time learning, stability, and error correction. An example will present biomimetic neural-network hardware that can be interfaced with the isolated spinal cord of a lower vertebrate to allow phase-locked real-time neural control. Another will present adaptive neural network control algorithms for functional electrical stimulation of the peripheral nervous system to provide desired movements of paralyzed limbs in rodents or people. Ultimately, the frontier lies in being able to utilize the adaptive neurotechnology to promote neuroplasticity in the living system on a long-time scale under co-adaptive conditions.
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...
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...
Neural networks for perception human and machine perception
Wechsler, Harry
1991-01-01
Neural Networks for Perception, Volume 1: Human and Machine Perception focuses on models for understanding human perception in terms of distributed computation and examples of PDP models for machine perception. This book addresses both theoretical and practical issues related to the feasibility of both explaining human perception and implementing machine perception in terms of neural network models. The book is organized into two parts. The first part focuses on human perception. Topics on network model ofobject recognition in human vision, the self-organization of functional architecture in t
An Adaptive-PSO-Based Self-Organizing RBF Neural Network.
Han, Hong-Gui; Lu, Wei; Hou, Ying; Qiao, Jun-Fei
2018-01-01
In this paper, a self-organizing radial basis function (SORBF) neural network is designed to improve both accuracy and parsimony with the aid of adaptive particle swarm optimization (APSO). In the proposed APSO algorithm, to avoid being trapped into local optimal values, a nonlinear regressive function is developed to adjust the inertia weight. Furthermore, the APSO algorithm can optimize both the network size and the parameters of an RBF neural network simultaneously. As a result, the proposed APSO-SORBF neural network can effectively generate a network model with a compact structure and high accuracy. Moreover, the analysis of convergence is given to guarantee the successful application of the APSO-SORBF neural network. Finally, multiple numerical examples are presented to illustrate the effectiveness of the proposed APSO-SORBF neural network. The results demonstrate that the proposed method is more competitive in solving nonlinear problems than some other existing SORBF neural networks.
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.
Analysis of convergence performance of neural networks ranking algorithm.
Zhang, Yongquan; Cao, Feilong
2012-10-01
The ranking problem is to learn a real-valued function which gives rise to a ranking over an instance space, which has gained much attention in machine learning in recent years. This article gives analysis of the convergence performance of neural networks ranking algorithm by means of the given samples and approximation property of neural networks. The upper bounds of convergence rate provided by our results can be considerably tight and independent of the dimension of input space when the target function satisfies some smooth condition. The obtained results imply that neural networks are able to adapt to ranking function in the instance space. Hence the obtained results are able to circumvent the curse of dimensionality on some smooth condition. Crown Copyright © 2012. Published by Elsevier Ltd. All rights reserved.
Artificial neural networks modeling gene-environment interaction
Directory of Open Access Journals (Sweden)
Günther Frauke
2012-05-01
Full Text Available Abstract Background Gene-environment interactions play an important role in the etiological pathway of complex diseases. An appropriate statistical method for handling a wide variety of complex situations involving interactions between variables is still lacking, especially when continuous variables are involved. The aim of this paper is to explore the ability of neural networks to model different structures of gene-environment interactions. A simulation study is set up to compare neural networks with standard logistic regression models. Eight different structures of gene-environment interactions are investigated. These structures are characterized by penetrance functions that are based on sigmoid functions or on combinations of linear and non-linear effects of a continuous environmental factor and a genetic factor with main effect or with a masking effect only. Results In our simulation study, neural networks are more successful in modeling gene-environment interactions than logistic regression models. This outperfomance is especially pronounced when modeling sigmoid penetrance functions, when distinguishing between linear and nonlinear components, and when modeling masking effects of the genetic factor. Conclusion Our study shows that neural networks are a promising approach for analyzing gene-environment interactions. Especially, if no prior knowledge of the correct nature of the relationship between co-variables and response variable is present, neural networks provide a valuable alternative to regression methods that are limited to the analysis of linearly separable data.
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
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.
Schmidt, M. A.; Goodwin, T. J.
2014-01-01
Brain derived neurotrophic factor (BDNF) is the main activity-dependent neurotrophin in the human nervous system. BDNF is implicated in production of new neurons from dentate gyrus stem cells (hippocampal neurogenesis), synapse formation, sprouting of new axons, growth of new axons, sprouting of new dendrites, and neuron survival. Alterations in the amount or activity of BDNF can produce significant detrimental changes to cortical function and synaptic transmission in the human brain. This can result in glial and neuronal dysfunction, which may contribute to a range of clinical conditions, spanning a number of learning, behavioral, and neurological disorders. There is an extensive body of work surrounding the BDNF molecular network, including BDNF gene polymorphisms, methylated BDNF gene promoters, multiple gene transcripts, varied BDNF functional proteins, and different BDNF receptors (whose activation differentially drive the neuron to neurogenesis or apoptosis). BDNF is also closely linked to mitochondrial biogenesis through PGC-1alpha, which can influence brain and muscle metabolic efficiency. BDNF AS A HUMAN SPACE FLIGHT COUNTERMEASURE TARGET Earth-based studies reveal that BDNF is negatively impacted by many of the conditions encountered in the space environment, including oxidative stress, radiation, psychological stressors, sleep deprivation, and many others. A growing body of work suggests that the BDNF network is responsive to a range of diet, nutrition, exercise, drug, and other types of influences. This section explores the BDNF network in the context of 1) protecting the brain and nervous system in the space environment, 2) optimizing neurobehavioral performance in space, and 3) reducing the residual effects of space flight on the nervous system on return to Earth
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)
Flow version of statistical neurodynamics for oscillator neural networks
Uchiyama, Satoki
2012-04-01
We consider a neural network of Stuart-Landau oscillators as an associative memory. This oscillator network with N elements is a system of an N-dimensional differential equation, works as an attractor neural network, and is expected to have no Lyapunov functions. Therefore, the technique of equilibrium statistical physics is not applicable to the study of this system in the thermodynamic limit. However, the simplicity of this system allows us to extend statistical neurodynamics [S. Amari, K. Maginu, Neural Netw. 1 (1988) 63-73], which was originally developed to analyse the discrete time evolution of the Hopfield model, into the version for continuous time evolution. We have developed and attempted to apply this method in the analysis of the phase transition of our model network.
Advances in neural networks computational and theoretical issues
Esposito, Anna; Morabito, Francesco
2015-01-01
This book collects research works that exploit neural networks and machine learning techniques from a multidisciplinary perspective. Subjects covered include theoretical, methodological and computational topics which are grouped together into chapters devoted to the discussion of novelties and innovations related to the field of Artificial Neural Networks as well as the use of neural networks for applications, pattern recognition, signal processing, and special topics such as the detection and recognition of multimodal emotional expressions and daily cognitive functions, and bio-inspired memristor-based networks. Providing insights into the latest research interest from a pool of international experts coming from different research fields, the volume becomes valuable to all those with any interest in a holistic approach to implement believable, autonomous, adaptive, and context-aware Information Communication Technologies.
Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.
Ly, Cheng
2015-12-01
Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.
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.
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.
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...
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…
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...
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.
Numerical analysis of modeling based on improved Elman neural network.
Jie, Shao; Li, Wang; WeiSong, Zhao; YaQin, Zhong; Malekian, Reza
2014-01-01
A modeling based on the improved Elman neural network (IENN) is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE) varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA) with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL) model, Chebyshev neural network (CNN) model, and basic Elman neural network (BENN) model, the proposed model has better performance.
Numerical Analysis of Modeling Based on Improved Elman Neural Network
Directory of Open Access Journals (Sweden)
Shao Jie
2014-01-01
Full Text Available A modeling based on the improved Elman neural network (IENN is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL model, Chebyshev neural network (CNN model, and basic Elman neural network (BENN model, the proposed model has better performance.
Neural networks for data compression and invariant image recognition
Gardner, Sheldon
1989-01-01
An approach to invariant image recognition (I2R), based upon a model of biological vision in the mammalian visual system (MVS), is described. The complete I2R model incorporates several biologically inspired features: exponential mapping of retinal images, Gabor spatial filtering, and a neural network associative memory. In the I2R model, exponentially mapped retinal images are filtered by a hierarchical set of Gabor spatial filters (GSF) which provide compression of the information contained within a pixel-based image. A neural network associative memory (AM) is used to process the GSF coded images. We describe a 1-D shape function method for coding of scale and rotationally invariant shape information. This method reduces image shape information to a periodic waveform suitable for coding as an input vector to a neural network AM. The shape function method is suitable for near term applications on conventional computing architectures equipped with VLSI FFT chips to provide a rapid image search capability.
Neural network approaches to dynamic collision-free trajectory generation.
Yang, S X; Meng, M
2001-01-01
In this paper, dynamic collision-free trajectory generation in a nonstationary environment is studied using biologically inspired neural network approaches. The proposed neural network is topologically organized, where the dynamics of each neuron is characterized by a shunting equation or an additive equation. The state space of the neural network can be either the Cartesian workspace or the joint space of multi-joint robot manipulators. There are only local lateral connections among neurons. The real-time optimal trajectory is generated through the dynamic activity landscape of the neural network without explicitly searching over the free space nor the collision paths, without explicitly optimizing any global cost functions, without any prior knowledge of the dynamic environment, and without any learning procedures. Therefore the model algorithm is computationally efficient. The stability of the neural network system is guaranteed by the existence of a Lyapunov function candidate. In addition, this model is not very sensitive to the model parameters. Several model variations are presented and the differences are discussed. As examples, the proposed models are applied to generate collision-free trajectories for a mobile robot to solve a maze-type of problem, to avoid concave U-shaped obstacles, to track a moving target and at the same to avoid varying obstacles, and to generate a trajectory for a two-link planar robot with two targets. The effectiveness and efficiency of the proposed approaches are demonstrated through simulation and comparison studies.
Neural networks within multi-core optic fibers.
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-07
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Neural networks within multi-core optic fibers
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-01
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Neural network 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.
Fernández, Michael; Caballero, Julio; Fernández, Leyden; Abreu, José Ignacio; Garriga, Miguel
2007-11-01
Development of novel computational approaches for modeling protein properties is a main goal in applied Proteomics. In this work, we reported the extension of the radial distribution function (RDF) scores formalism to proteins for encoding 3D structural information with modeling purposes. Protein-RDF (P-RDF) scores measure spherical distributions on protein 3D structure of 48 amino acids/residues properties selected from the AAindex data base. P-RDF scores were tested for building predictive models of the change of thermal unfolding Gibbs free energy change (DeltaDeltaG) of chymotrypsin inhibitor 2 upon mutations. In this sense, an ensemble of Bayesian-Regularized Genetic Neural Networks (BRGNNs) yielded an optimum nonlinear model for the conformational stability. The ensemble predictor described about 84% and 70% variance of the data in training and test sets, respectively.
Ross, Muriel D.; Meyer, Glenn; Lam, Tony; Cutler, Lynn; Vaziri, Parshaw
1990-01-01
Computer-assisted reconstructions of small parts of the macular neural network show how the nerve terminals and receptive fields are organized in 3-dimensional space. This biological neural network is anatomically organized for parallel distributed processing of information. Processing appears to be more complex than in computer-based neural network, because spatiotemporal factors figure into synaptic weighting. Serial reconstruction data show anatomical arrangements which suggest that (1) assemblies of cells analyze and distribute information with inbuilt redundancy, to improve reliability; (2) feedforward/feedback loops provide the capacity for presynaptic modulation of output during processing; (3) constrained randomness in connectivities contributes to adaptability; and (4) local variations in network complexity permit differing analyses of incoming signals to take place simultaneously. The last inference suggests that there may be segregation of information flow to central stations subserving particular functions.
He, Yan-Lin; Xu, Yuan; Geng, Zhi-Qiang; Zhu, Qun-Xiong
2016-03-01
In this paper, a hybrid robust model based on an improved functional link neural network integrating with partial least square (IFLNN-PLS) is proposed. Firstly, an improved functional link neural network with small norm of expanded weights and high input-output correlation (SNEWHIOC-FLNN) was proposed for enhancing the generalization performance of FLNN. Unlike the traditional FLNN, the expanded variables of the original inputs are not directly used as the inputs in the proposed SNEWHIOC-FLNN model. The original inputs are attached to some small norm of expanded weights. As a result, the correlation coefficient between some of the expanded variables and the outputs is enhanced. The larger the correlation coefficient is, the more relevant the expanded variables tend to be. In the end, the expanded variables with larger correlation coefficient are selected as the inputs to improve the performance of the traditional FLNN. In order to test the proposed SNEWHIOC-FLNN model, three UCI (University of California, Irvine) regression datasets named Housing, Concrete Compressive Strength (CCS), and Yacht Hydro Dynamics (YHD) are selected. Then a hybrid model based on the improved FLNN integrating with partial least square (IFLNN-PLS) was built. In IFLNN-PLS model, the connection weights are calculated using the partial least square method but not the error back propagation algorithm. Lastly, IFLNN-PLS was developed as an intelligent measurement model for accurately predicting the key variables in the Purified Terephthalic Acid (PTA) process and the High Density Polyethylene (HDPE) process. Simulation results illustrated that the IFLNN-PLS could significant improve the prediction performance. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.
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 ...
Neural Network Analysis and Evaluation of the Fetal Heart Rate
Directory of Open Access Journals (Sweden)
Yasuaki Noguchi
2009-01-01
Full Text Available The aim of the present study is to obtain a highly objective automatic fetal heart rate (FHR diagnosis. The neural network software was composed of three layers with the back propagation, to which 8 FHR data, including sinusoidal FHR, were input and the system was educated by the data of 20 cases with a known outcome. The output was the probability of a normal, intermediate, or pathologic outcome. The neural index studied prolonged monitoring. The neonatal states and the FHR score strongly correlated with the outcome probability. The neural index diagnosis was correct. The completed software was transferred to other computers, where the system function was correct.
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.
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.
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.
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.
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.
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.
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.
Forecast of consumer behaviour based on neural networks models comparison
Directory of Open Access Journals (Sweden)
Michael Štencl
2012-01-01
Full Text Available The aim of this article is comparison of accuracy level of forecasted values of several artificial neural network models. The comparison is performed on datasets of Czech household consumption values. Several statistical models often resolve this task with more or fewer restrictions. In previous work where models’ input conditions were not so strict and model with missing data was used (the time series didn’t contain many values we have obtained comparably good results with artificial neural networks. Two views – practical and theoretical, motivate the purpose of this study. Forecasting models for medium term prognosis of the main trends of Czech household consumption is part of the faculty research design grant MSM 6215648904/03/02 (Sub-task 5.3 which defines the practical purpose. Testing of nonlinear autoregressive artificial neural network model compared with feed-forward neural network and radial basis function neural network defines the theoretical purpose. The performance metrics of the models were evaluated using a combination of common error metrics, namely Correlation Coefficient and Mean Square Error, together with the number of epochs and/or main prediction error.
PREDICTING CUSTOMER CHURN IN BANKING INDUSTRY USING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Alisa Bilal Zorić
2016-03-01
Full Text Available The aim of this article is to present a case study of usage of one of the data mining methods, neural network, in knowledge discovery from databases in the banking industry. Data mining is automated process of analysing, organization or grouping a large set of data from different perspectives and summarizing it into useful information using special algorithms. Data mining can help to resolve banking problems by finding some regularity, causality and correlation to business information which are not visible at first sight because they are hidden in large amounts of data. In this paper, we used one of the data mining methods, neural network, within the software package Alyuda NeuroInteligence to predict customer churn in bank. The focus on customer churn is to determinate the customers who are at risk of leaving and analysing whether those customers are worth retaining. Neural network is statistical learning model inspired by biological neural and it is used to estimate or approximate functions that can depend on a large number of inputs which are generally unknown. Although the method itself is complicated, there are tools that enable the use of neural networks without much prior knowledge of how they operate. The results show that clients who use more bank services (products are more loyal, so bank should focus on those clients who use less than three products, and offer them products according to their needs. Similar results are obtained for different network topologies.
Neural-network-based fuzzy logic decision systems
Kulkarni, Arun D.; Giridhar, G. B.; Coca, Praveen
1994-10-01
During the last few years there has been a large and energetic upswing in research efforts aimed at synthesizing fuzzy logic with neural networks. This combination of neural networks and fuzzy logic seems natural because the two approaches generally attack the design of `intelligent' system from quite different angles. Neural networks provide algorithms for learning, classification, and optimization whereas fuzzy logic often deals with issues such as reasoning in a high (semantic or linguistic) level. Consequently the two technologies complement each other. In this paper, we combine neural networks with fuzzy logic techniques. We propose an artificial neural network (ANN) model for a fuzzy logic decision system. The model consists of six layers. The first three layers map the input variables to fuzzy set membership functions. The last three layers implement the decision rules. The model learns the decision rules using a supervised gradient descent procedure. As an illustration we considered two examples. The first example deals with pixel classification in multispectral satellite images. In our second example we used the fuzzy decision system to analyze data from magnetic resonance imaging (MRI) scans for tissue classification.
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.
Coded Network Function Virtualization
DEFF Research Database (Denmark)
Al-Shuwaili, A.; Simone, O.; Kliewer, J.
2016-01-01
Network function virtualization (NFV) prescribes the instantiation of network functions on general-purpose network devices, such as servers and switches. While yielding a more flexible and cost-effective network architecture, NFV is potentially limited by the fact that commercial off-the-shelf ha......Network function virtualization (NFV) prescribes the instantiation of network functions on general-purpose network devices, such as servers and switches. While yielding a more flexible and cost-effective network architecture, NFV is potentially limited by the fact that commercial off...
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 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.
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...
Autonomic neural functions in space.
Mano, T
2005-08-01
Autonomic neural functions are important to regulate vital functions in the living body. There are different methods to evaluate indirectly and directly autonomic, sympathetic and parasympathetic, neural functions of human body. Among various methods, microneurography is a technique to evaluate directly sympathetic neural functions in humans. Using this technique sympathetic neural traffic leading to skeletal muscles (muscle sympathetic nerve activity; MSNA) can be recorded from human peripheral nerves in situ. MSNA plays essentially important roles to maintain blood pressure homeostasis against gravity. Orthostatic intolerance is an important problem as an autonomic dysfunction encountered after exposure of human beings to microgravity. There exist at least two different types of sympathetic neural responses, low and high responders to orthostatic stress in orthostatic hypotension seen in neurological disorders. To answer the question if post-spaceflight orthostatic intolerance is induced by low or high MSNA responses to orthostatic stress, MSNA was microneurographically recorded for the first time before, during and after spaceflight in 1998 under Neurolab international research project. The same activity has been recorded during and/or after ground-based short- and long-term simulations of microgravity. MSNA was rather enhanced on the 12(th) and 13(th) day of spaceflight and just after landing day. Postflight MSNA response to head-up tilt was well preserved in astronauts who were orthostatically well tolerant. MSNA was suppressed during short-term simulation of microgravity less than 2 hours but was enhanced after long-term simulation of microgravity more than 3 days. Orthostatic intolerance after exposure to long-term simulation of microgravity was associated with reduced MSNA response to orthostatic stress with impaired baroreflex functions. These findings obtained from MSNA recordings in subjects exposed to space as well as short- and long-term simulations of
A general regression neural network and Monte Carlo simulation model for predicting survival and growth of Salmonella on raw chicken skin as a function of serotype (Typhimurium, Kentucky, Hadar), temperature (5 to 50C) and time (0 to 8 h) was developed. Poultry isolates of Salmonella with natural r...
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.
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.
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
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.
Neural Network Predictive Control for Vanadium Redox Flow Battery
Directory of Open Access Journals (Sweden)
Hai-Feng Shen
2013-01-01
Full Text Available The vanadium redox flow battery (VRB is a nonlinear system with unknown dynamics and disturbances. The flowrate of the electrolyte is an important control mechanism in the operation of a VRB system. Too low or too high flowrate is unfavorable for the safety and performance of VRB. This paper presents a neural network predictive control scheme to enhance the overall performance of the battery. A radial basis function (RBF network is employed to approximate the dynamics of the VRB system. The genetic algorithm (GA is used to obtain the optimum initial values of the RBF network parameters. The gradient descent algorithm is used to optimize the objective function of the predictive controller. Compared with the constant flowrate, the simulation results show that the flowrate optimized by neural network predictive controller can increase the power delivered by the battery during the discharge and decrease the power consumed during the charge.
Bilingual Lexical Interactions in an Unsupervised Neural Network Model
Zhao, Xiaowei; Li, Ping
2010-01-01
In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…
RBF neural network based H∞ synchronization for unknown chaotic ...
Indian Academy of Sciences (India)
MS received 9 February 2010; accepted 24 May 2010. Abstract. In this paper, we propose a new H∞ synchronization strategy, called a. Radial Basis Function Neural Network H∞ synchronization (RBFNNHS) strategy, for unknown chaotic systems in the presence of external disturbance. In the pro- posed framework, a ...
Artificial Neural Network Based State Estimators Integrated into Kalmtool
DEFF Research Database (Denmark)
Bayramoglu, Enis; Ravn, Ole; Poulsen, Niels Kjølstad
2012-01-01
In this paper we present a toolbox enabling easy evaluation and comparison of dierent ltering algorithms. The toolbox is called Kalmtool and is a set of MATLAB tools for state estimation of nonlinear systems. The toolbox now contains functions for Articial Neural Network Based State Estimation...
Role of neural network models for developing speech systems
Indian Academy of Sciences (India)
These prosody models are further examined for applications such as text to speech synthesis, speech recognition, speaker recognition and language identiﬁcation. Neural network models in voice conversion system are explored for capturing the mapping functions between source and target speakers at source, system and ...
Bayesian and neural networks for preliminary ship design
DEFF Research Database (Denmark)
Clausen, H. B.; Lützen, Marie; Friis-Hansen, Andreas
2001-01-01
000 ships is acquired and various methods for derivation of empirical relations are employed. A regression analysis is carried out to fit functions to the data. Further, the data are used to learn Bayesian and neural networks to encode the relations between the characteristics. On the basis...
Wei-Bo Chen; Wen-Cheng Liu
2015-01-01
In this study, two artificial neural network models (i.e., a radial basis function neural network, RBFN, and an adaptive neurofuzzy inference system approach, ANFIS) and a multilinear regression (MLR) model were developed to simulate the DO, TP, Chl a, and SD in the Mingder Reservoir of central Taiwan. The input variables of the neural network and the MLR models were determined using linear regression. The performances were evaluated using the RBFN, ANFIS, and MLR models based on statistical ...
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
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...
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.
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.
Nano-topography Enhances Communication in Neural Cells Networks
Onesto, V.
2017-08-23
Neural cells are the smallest building blocks of the central and peripheral nervous systems. Information in neural networks and cell-substrate interactions have been heretofore studied separately. Understanding whether surface nano-topography can direct nerve cells assembly into computational efficient networks may provide new tools and criteria for tissue engineering and regenerative medicine. In this work, we used information theory approaches and functional multi calcium imaging (fMCI) techniques to examine how information flows in neural networks cultured on surfaces with controlled topography. We found that substrate roughness Sa affects networks topology. In the low nano-meter range, S-a = 0-30 nm, information increases with Sa. Moreover, we found that energy density of a network of cells correlates to the topology of that network. This reinforces the view that information, energy and surface nano-topography are tightly inter-connected and should not be neglected when studying cell-cell interaction in neural tissue repair and regeneration.
The role of symmetry in neural networks and their Laplacian spectra.
de Lange, Siemon C; van den Heuvel, Martijn P; de Reus, Marcel A
2016-11-01
Human and animal nervous systems constitute complexly wired networks that form the infrastructure for neural processing and integration of information. The organization of these neural networks can be analyzed using the so-called Laplacian spectrum, providing a mathematical tool to produce systems-level network fingerprints. In this article, we examine a characteristic central peak in the spectrum of neural networks, including anatomical brain network maps of the mouse, cat and macaque, as well as anatomical and functional network maps of human brain connectivity. We link the occurrence of this central peak to the level of symmetry in neural networks, an intriguing aspect of network organization resulting from network elements that exhibit similar wiring patterns. Specifically, we propose a measure to capture the global level of symmetry of a network and show that, for both empirical networks and network models, the height of the main peak in the Laplacian spectrum is strongly related to node symmetry in the underlying network. Moreover, examination of spectra of duplication-based model networks shows that neural spectra are best approximated using a trade-off between duplication and diversification. Taken together, our results facilitate a better understanding of neural network spectra and the importance of symmetry in neural networks. Copyright © 2016 Elsevier Inc. All rights reserved.
Dominey, Peter Ford; Inui, Toshio; Hoen, Michel
2009-01-01
A central issue in cognitive neuroscience today concerns how distributed neural networks in the brain that are used in language learning and processing can be involved in non-linguistic cognitive sequence learning. This issue is informed by a wealth of functional neurophysiology studies of sentence comprehension, along with a number of recent studies that examined the brain processes involved in learning non-linguistic sequences, or artificial grammar learning (AGL). The current research attempts to reconcile these data with several current neurophysiologically based models of sentence processing, through the specification of a neural network model whose architecture is constrained by the known cortico-striato-thalamo-cortical (CSTC) neuroanatomy of the human language system. The challenge is to develop simulation models that take into account constraints both from neuranatomical connectivity, and from functional imaging data, and that can actually learn and perform the same kind of language and artificial syntax tasks. In our proposed model, structural cues encoded in a recurrent cortical network in BA47 activate a CSTC circuit to modulate the flow of lexical semantic information from BA45 to an integrated representation of meaning at the sentence level in BA44/6. During language acquisition, corticostriatal plasticity is employed to allow closed class structure to drive thematic role assignment. From the AGL perspective, repetitive internal structure in the AGL strings is encoded in BA47, and activates the CSTC circuit to predict the next element in the sequence. Simulation results from Caplan's [Caplan, D., Baker, C., & Dehaut, F. (1985). Syntactic determinants of sentence comprehension in aphasia. Cognition, 21, 117-175] test of syntactic comprehension, and from Gomez and Schvaneveldts' [Gomez, R. L., & Schvaneveldt, R. W. (1994). What is learned from artificial grammars?. Transfer tests of simple association. Journal of Experimental Psychology: Learning
Functional neural anatomy of talent.
Kalbfleisch, M Layne
2004-03-01
The terms gifted, talented, and intelligent all have meanings that suggest an individual's highly proficient or exceptional performance in one or more specific areas of strength. Other than Spearman's g, which theorizes about a general elevated level of potential or ability, more contemporary theories of intelligence are based on theoretical models that define ability or intelligence according to a priori categories of specific performance. Recent studies in cognitive neuroscience report on the neural basis of g from various perspectives such as the neural speed theory and the efficiency of prefrontal function. Exceptional talent is the result of interactions between goal-directed behavior and nonvolitional perceptual processes in the brain that have yet to be fully characterized and understood by the fields of psychology and cognitive neuroscience. Some developmental studies report differences in region-specific neural activation, recruitment patterns, and reaction times in subjects who are identified with high IQ scores according to traditional scales of assessment such as the WISC-III or Stanford-Binet. Although as cases of savants and prodigies illustrate, talent is not synonymous with high IQ. This review synthesizes information from the fields of psychometrics and gifted education, with findings from the neurosciences on the neural basis of intelligence, creativity, profiles of expert performers, cognitive function, and plasticity to suggest a paradigm for investigating talent as the maximal and productive use of either or both of one's high level of general intelligence or domain-specific ability. Anat Rec (Part B: New Anat) 277B:21-36, 2004. Copyright 2004 Wiley-Liss, Inc.
Computational modeling of neural plasticity for self-organization of neural networks.
Chrol-Cannon, Joseph; Jin, Yaochu
2014-11-01
Self-organization in biological nervous systems during the lifetime is known to largely occur through a process of plasticity that is dependent upon the spike-timing activity in connected neurons. In the field of computational neuroscience, much effort has been dedicated to building up computational models of neural plasticity to replicate experimental data. Most recently, increasing attention has been paid to understanding the role of neural plasticity in functional and structural neural self-organization, as well as its influence on the learning performance of neural networks for accomplishing machine learning tasks such as classification and regression. Although many ideas and hypothesis have been suggested, the relationship between the structure, dynamics and learning performance of neural networks remains elusive. The purpose of this article is to review the most important computational models for neural plasticity and discuss various ideas about neural plasticity's role. Finally, we suggest a few promising research directions, in particular those along the line that combines findings in computational neuroscience and systems biology, and their synergetic roles in understanding learning, memory and cognition, thereby bridging the gap between computational neuroscience, systems biology and computational intelligence. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.
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
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.
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.
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.
Optimizing neural network models: motivation and case studies
Harp, S A; T. Samad
2012-01-01
Practical successes have been achieved with neural network models in a variety of domains, including energy-related industry. The large, complex design space presented by neural networks is only minimally explored in current practice. The satisfactory results that nevertheless have been obtained testify that neural networks are a robust modeling technology; at the same time, however, the lack of a systematic design approach implies that the best neural network models generally rem...
Dynamic Object Identification with SOM-based neural networks
Directory of Open Access Journals (Sweden)
Aleksey Averkin
2014-03-01
Full Text Available In this article a number of neural networks based on self-organizing maps, that can be successfully used for dynamic object identification, is described. Unique SOM-based modular neural networks with vector quantized associative memory and recurrent self-organizing maps as modules are presented. The structured algorithms of learning and operation of such SOM-based neural networks are described in details, also some experimental results and comparison with some other neural networks are given.
Stock Price Prediction Based on Procedural Neural Networks
Jiuzhen Liang; Wei Song; Mei Wang
2011-01-01
We present a spatiotemporal model, namely, procedural neural networks for stock price prediction. Compared with some successful traditional models on simulating stock market, such as BNN (backpropagation neural networks, HMM (hidden Markov model) and SVM (support vector machine)), the procedural neural network model processes both spacial and temporal information synchronously without slide time window, which is typically used in the well-known recurrent neural networks. Two differen...
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.
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 ...
Epileptiform spike detection via convolutional neural networks
DEFF Research Database (Denmark)
Johansen, Alexander Rosenberg; Jin, Jing; Maszczyk, Tomasz
2016-01-01
The EEG of epileptic patients often contains sharp waveforms called "spikes", occurring between seizures. Detecting such spikes is crucial for diagnosing epilepsy. In this paper, we develop a convolutional neural network (CNN) for detecting spikes in EEG of epileptic patients in an automated...
Artificial neural networks and support vector mac
Indian Academy of Sciences (India)
Quantitative structure-property relationships of electroluminescent materials: Artificial neural networks and support vector machines to predict electroluminescence of organic molecules. ALANA FERNANDES GOLIN and RICARDO STEFANI. ∗. Laboratório de Estudos de Materiais (LEMAT), Instituto de Ciências Exatas e da ...
Neural Networks for protein Structure Prediction
DEFF Research Database (Denmark)
Bohr, Henrik
1998-01-01
This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...
Towards semen quality assessment using neural networks
DEFF Research Database (Denmark)
Linneberg, Christian; Salamon, P.; Svarer, C.
1994-01-01
The paper presents the methodology and results from a neural net based classification of human sperm head morphology. The methodology uses a preprocessing scheme in which invariant Fourier descriptors are lumped into “energy” bands. The resulting networks are pruned using optimal brain damage...
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...
Convolutional Neural Networks - Generalizability and Interpretations
DEFF Research Database (Denmark)
Malmgren-Hansen, David
from data despite it being limited in amount or context representation. Within Machine Learning this thesis focuses on Convolutional Neural Networks for Computer Vision. The research aims to answer how to explore a model's generalizability to the whole population of data samples and how to interpret...
Visualization of neural networks using saliency maps
DEFF Research Database (Denmark)
Mørch, Niels J.S.; Kjems, Ulrik; Hansen, Lars Kai
1995-01-01
The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations...
Separable explanations of neural network decisions
DEFF Research Database (Denmark)
Rieger, Laura
2017-01-01
Deep Taylor Decomposition is a method used to explain neural network decisions. When applying this method to non-dominant classifications, the resulting explanation does not reflect important features for the chosen classification. We propose that this is caused by the dense layers and propose...
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....
Empirical generalization assessment of neural network models
DEFF Research Database (Denmark)
Larsen, Jan; Hansen, Lars Kai
1995-01-01
This paper addresses the assessment of generalization performance of neural network models by use of empirical techniques. We suggest to use the cross-validation scheme combined with a resampling technique to obtain an estimate of the generalization performance distribution of a specific model...
Localizing Tortoise Nests by Neural Networks.
Directory of Open Access Journals (Sweden)
Roberto Barbuti
Full Text Available The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating. Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN. We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours, the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition.
Applying Artificial Neural Networks for Face Recognition
Directory of Open Access Journals (Sweden)
Thai Hoang Le
2011-01-01
Full Text Available This paper introduces some novel models for all steps of a face recognition system. In the step of face detection, we propose a hybrid model combining AdaBoost and Artificial Neural Network (ABANN to solve the process efficiently. In the next step, labeled faces detected by ABANN will be aligned by Active Shape Model and Multi Layer Perceptron. In this alignment step, we propose a new 2D local texture model based on Multi Layer Perceptron. The classifier of the model significantly improves the accuracy and the robustness of local searching on faces with expression variation and ambiguous contours. In the feature extraction step, we describe a methodology for improving the efficiency by the association of two methods: geometric feature based method and Independent Component Analysis method. In the face matching step, we apply a model combining many Neural Networks for matching geometric features of human face. The model links many Neural Networks together, so we call it Multi Artificial Neural Network. MIT + CMU database is used for evaluating our proposed methods for face detection and alignment. Finally, the experimental results of all steps on CallTech database show the feasibility of our proposed model.
drinking water treatment using artificial neural network
African Journals Online (AJOL)
ogwueleka
synaptic weights are used to store the knowledge.” The neural network approach is a branch of artificial intelligence. The ANN is based on a model of the human neurological system that consists of basic computing elements (called neurons) interconnected together (Figure 1). The model used for all classification attempts.
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)
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
Nonlinear Time Series Analysis via Neural Networks
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Neural networks, penalty logic and optimality theory
Blutner, R.; Benz, A.; Blutner, R.
2009-01-01
Ever since the discovery of neural networks, there has been a controversy between two modes of information processing. On the one hand, symbolic systems have proven indispensable for our understanding of higher intelligence, especially when cognitive domains like language and reasoning are examined.
Image inpainting using a neural network
Directory of Open Access Journals (Sweden)
Gapon Nikolay
2017-01-01
Full Text Available The paper describes a new method of two-dimensional signals reconstruction by restoring static images. A new method of spatial reconstruction of static images based on a geometric model using a neural network is proposed, it is based on the search for similar blocks and copying them into the region of distorted or missing pixel values.
Foetal ECG recovery using dynamic neural networks.
Camps-Valls, Gustavo; Martínez-Sober, Marcelino; Soria-Olivas, Emilio; Magdalena-Benedito, Rafael; Calpe-Maravilla, Javier; Guerrero-Martínez, Juan
2004-07-01
Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coefficient) and statistical (analysis of variance, ANOVA) measures allows us to select the best recovery model. Finally, finite impulse response (FIR) and gamma neural networks are included in the adaptive noise cancellation (ANC) scheme in order to provide highly non-linear, dynamic capabilities to the recovery model. Neural networks are benchmarked with classical adaptive methods such as the least mean squares (LMS) and the normalized LMS (NLMS) algorithms in simulated and real registers and some conclusions are drawn. For synthetic registers, the most determinant factor in the identification of the models is the foetal-maternal signal-to-noise ratio (SNR). In addition, as the electromyogram contribution becomes more relevant, neural networks clearly outperform the LMS-based algorithm. From the ANOVA test, we found statistical differences between LMS-based models and neural models when complex situations (high foetal-maternal and foetal-noise SNRs) were present. These conclusions were confirmed after doing robustness tests on synthetic registers, visual inspection of the recovered signals and calculation of the recognition rates of foetal R-peaks for real situations. Finally, the best compromise between model complexity and outcomes was provided by the FIR neural network. Both
MBVCNN: Joint convolutional neural networks method for image recognition
Tong, Tong; Mu, Xiaodong; Zhang, Li; Yi, Zhaoxiang; Hu, Pei
2017-05-01
Aiming at the problem of objects in image recognition rectangle, but objects which are input into convolutional neural networks square, the object recognition model was put forward which was based on BING method to realize object estimate, used vectorization of convolutional neural networks to realize input square image in convolutional networks, therefore, built joint convolution neural networks, which achieve multiple size image input. Verified by experiments, the accuracy of multi-object image recognition was improved by 6.70% compared with single vectorization of convolutional neural networks. Therefore, image recognition method of joint convolutional neural networks can enhance the accuracy in image recognition, especially for target in rectangular shape.
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...
A linear model for characterization of synchronization frequencies of neural networks.
Lv, Peili; Hu, Xintao; Lv, Jinglei; Han, Junwei; Guo, Lei; Liu, Tianming
2014-02-01
The synchronization frequency of neural networks and its dynamics have important roles in deciphering the working mechanisms of the brain. It has been widely recognized that the properties of functional network synchronization and its dynamics are jointly determined by network topology, network connection strength, i.e., the connection strength of different edges in the network, and external input signals, among other factors. However, mathematical and computational characterization of the relationships between network synchronization frequency and these three important factors are still lacking. This paper presents a novel computational simulation framework to quantitatively characterize the relationships between neural network synchronization frequency and network attributes and input signals. Specifically, we constructed a series of neural networks including simulated small-world networks, real functional working memory network derived from functional magnetic resonance imaging, and real large-scale structural brain networks derived from diffusion tensor imaging, and performed synchronization simulations on these networks via the Izhikevich neuron spiking model. Our experiments demonstrate that both of the network synchronization strength and synchronization frequency change according to the combination of input signal frequency and network self-synchronization frequency. In particular, our extensive experiments show that the network synchronization frequency can be represented via a linear combination of the network self-synchronization frequency and the input signal frequency. This finding could be attributed to an intrinsically-preserved principle in different types of neural systems, offering novel insights into the working mechanism of neural systems.
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
neural network based load frequency control for restructuring power
African Journals Online (AJOL)
2012-03-01
Mar 1, 2012 ... Abstract. In this study, an artificial neural network (ANN) application of load frequency control. (LFC) of a Multi-Area power system by using a neural network controller is presented. The comparison between a conventional Proportional Integral (PI) controller and the proposed artificial neural networks ...
Time series prediction with simple recurrent neural networks ...
African Journals Online (AJOL)
Simple recurrent neural networks are widely used in time series prediction. Most researchers and application developers often choose arbitrarily between Elman or Jordan simple recurrent neural networks for their applications. A hybrid of the two called Elman-Jordan (or Multi-recurrent) neural network is also being used.
New Neural Network Methods for Forecasting Regional Employment
Patuelli, R.; Reggiani, A; Nijkamp, P.; Blien, U.
2006-01-01
In this paper, a set of neural network (NN) models is developed to compute short-term forecasts of regional employment patterns in Germany. Neural networks are modern statistical tools based on learning algorithms that are able to process large amounts of data. Neural networks are enjoying
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.
Algorithm For A Self-Growing Neural Network
Cios, Krzysztof J.
1996-01-01
CID3 algorithm simulates self-growing neural network. Constructs decision trees equivalent to hidden layers of neural network. Based on ID3 algorithm, which dynamically generates decision tree while minimizing entropy of information. CID3 algorithm generates feedforward neural network by use of either crisp or fuzzy measure of entropy.
Optical implementation of neural networks
Yu, Francis T. S.; Guo, Ruyan
2002-12-01
An adaptive optical neuro-computing (ONC) using inexpensive pocket size liquid crystal televisions (LCTVs) had been developed by the graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8×8=64 neurons, it can be easily extended to 16×20=320 neurons. The major advantages of this LCTV architecture as compared with other reported ONCs, are low cost and the flexibility to operate. To test the performance, several neural net models are used. These models are Interpattern Association, Hetero-association and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.
Identifying Jets Using Artifical Neural Networks
Rosand, Benjamin; Caines, Helen; Checa, Sofia
2017-09-01
We investigate particle jet interactions with the Quark Gluon Plasma (QGP) using artificial neural networks modeled on those used in computer image recognition. We create jet images by binning jet particles into pixels and preprocessing every image. We analyzed the jets with a Multi-layered maxout network and a convolutional network. We demonstrate each network's effectiveness in differentiating simulated quenched jets from unquenched jets, and we investigate the method that the network uses to discriminate among different quenched jet simulations. Finally, we develop a greater understanding of the physics behind quenched jets by investigating what the network learnt as well as its effectiveness in differentiating samples. Yale College Freshman Summer Research Fellowship in the Sciences and Engineering.
THE USE OF NEURAL NETWORK TECHNOLOGY TO MODEL SWIMMING PERFORMANCE
Directory of Open Access Journals (Sweden)
António José Silva
2007-03-01
Full Text Available The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility, swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8% between true and estimated performances is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports
Building footprint extraction from digital surface models using neural networks
Davydova, Ksenia; Cui, Shiyong; Reinartz, Peter
2016-10-01
Two-dimensional building footprints are a basis for many applications: from cartography to three-dimensional building models generation. Although, many methodologies have been proposed for building footprint extraction, this topic remains an open research area. Neural networks are able to model the complex relationships between the multivariate input vector and the target vector. Based on these abilities we propose a methodology using neural networks and Markov Random Fields (MRF) for automatic building footprint extraction from normalized Digital Surface Model (nDSM) and satellite images within urban areas. The proposed approach has mainly two steps. In the first step, the unary terms are learned for the MRF energy function by a four-layer neural network. The neural network is learned on a large set of patches consisting of both nDSM and Normalized Difference Vegetation Index (NDVI). Then prediction is performed to calculate the unary terms that are used in the MRF. In the second step, the energy function is minimized using a maxflow algorithm, which leads to a binary building mask. The building extraction results are compared with available ground truth. The comparison illustrates the efficiency of the proposed algorithm which can extract approximately 80% of buildings from nDSM with high accuracy.
Neuromodulatory connectivity defines the structure of a behavioral neural network.
Diao, Feici; Elliott, Amicia D; Diao, Fengqiu; Shah, Sarav; White, Benjamin H
2017-11-22
Neural networks are typically defined by their synaptic connectivity, yet synaptic wiring diagrams often provide limited insight into network function. This is due partly to the importance of non-synaptic communication by neuromodulators, which can dynamically reconfigure circuit activity to alter its output. Here, we systematically map the patterns of neuromodulatory connectivity in a network that governs a developmentally critical behavioral sequence in Drosophila. This sequence, which mediates pupal ecdysis, is governed by the serial release of several key factors, which act both somatically as hormones and within the brain as neuromodulators. By identifying and characterizing the functions of the neuronal targets of these factors, we find that they define hierarchically organized layers of the network controlling the pupal ecdysis sequence: a modular input layer, an intermediate central pattern generating layer, and a motor output layer. Mapping neuromodulatory connections in this system thus defines the functional architecture of the network.
Artificial neural networks as quantum associative memory
Hamilton, Kathleen; Schrock, Jonathan; Imam, Neena; Humble, Travis
We present results related to the recall accuracy and capacity of Hopfield networks implemented on commercially available quantum annealers. The use of Hopfield networks and artificial neural networks as content-addressable memories offer robust storage and retrieval of classical information, however, implementation of these models using currently available quantum annealers faces several challenges: the limits of precision when setting synaptic weights, the effects of spurious spin-glass states and minor embedding of densely connected graphs into fixed-connectivity hardware. We consider neural networks which are less than fully-connected, and also consider neural networks which contain multiple sparsely connected clusters. We discuss the effect of weak edge dilution on the accuracy of memory recall, and discuss how the multiple clique structure affects the storage capacity. Our work focuses on storage of patterns which can be embedded into physical hardware containing n States Department of Defense and used resources of the Computational Research and Development Programs as Oak Ridge National Laboratory under Contract No. DE-AC0500OR22725 with the U. S. Department of Energy.
Guo, Xinyu; Dominick, Kelli C; Minai, Ali A; Li, Hailong; Erickson, Craig A; Lu, Long J
2017-01-01
The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t-test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre
Directory of Open Access Journals (Sweden)
Xinyu Guo
2017-08-01
Full Text Available The whole-brain functional connectivity (FC pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes. Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150. Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t-test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross
Cheng, Long; Hou, Zeng-Guang; Lin, Yingzi; Tan, Min; Zhang, Wenjun Chris; Wu, Fang-Xiang
2011-05-01
A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.
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.
Matrix representation of a Neural Network
DEFF Research Database (Denmark)
Christensen, Bjørn Klint
Processing, by David Rummelhart (Rummelhart 1986) for an easy-to-read introduction. What the paper does explain is how a matrix representation of a neural net allows for a very simple implementation. The matrix representation is introduced in (Rummelhart 1986, chapter 9), but only for a two-layer linear...... network and the feedforward algorithm. This paper develops the idea further to three-layer non-linear networks and the backpropagation algorithm. Figure 1 shows the layout of a three-layer network. There are I input nodes, J hidden nodes and K output nodes all indexed from 0. Bias-node for the hidden...
Neural networks: Application to medical imaging
Clarke, Laurence P.
1994-01-01
The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.
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.
Optical neural network system for pose determination of spinning satellites
Lee, Andrew; Casasent, David
1990-01-01
An optical neural network architecture and algorithm based on a Hopfield optimization network are presented for multitarget tracking. This tracker utilizes a neuron for every possible target track, and a quadratic energy function of neural activities which is minimized using gradient descent neural evolution. The neural net tracker is demonstrated as part of a system for determining position and orientation (pose) of spinning satellites with respect to a robotic spacecraft. The input to the system is time sequence video from a single camera. Novelty detection and filtering are utilized to locate and segment novel regions from the input images. The neural net multitarget tracker determines the correspondences (or tracks) of the novel regions as a function of time, and hence the paths of object (satellite) parts. The path traced out by a given part or region is approximately elliptical in image space, and the position, shape and orientation of the ellipse are functions of the satellite geometry and its pose. Having a geometric model of the satellite, and the elliptical path of a part in image space, the three-dimensional pose of the satellite is determined. Digital simulation results using this algorithm are presented for various satellite poses and lighting conditions.
Neural networks for process control and optimization: two industrial applications.
Bloch, Gérard; Denoeux, Thierry
2003-01-01
The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.
Energy Technology Data Exchange (ETDEWEB)
1991-01-01
The present conference the application of neural networks to associative memories, neurorecognition, hybrid systems, supervised and unsupervised learning, image processing, neurophysiology, sensation and perception, electrical neurocomputers, optimization, robotics, machine vision, sensorimotor control systems, and neurodynamics. Attention is given to such topics as optimal associative mappings in recurrent networks, self-improving associative neural network models, fuzzy activation functions, adaptive pattern recognition with sparse associative networks, efficient question-answering in a hybrid system, the use of abstractions by neural networks, remote-sensing pattern classification, speech recognition with guided propagation, inverse-step competitive learning, and rotational quadratic function neural networks. Also discussed are electrical load forecasting, evolutionarily stable and unstable strategies, the capacity of recurrent networks, neural net vs control theory, perceptrons for image recognition, storage capacity of bidirectional associative memories, associative random optimization for control, automatic synthesis of digital neural architectures, self-learning robot vision, and the associative dynamics of chaotic neural networks.
Neural Network Based Intelligent Sootblowing System
Energy Technology Data Exchange (ETDEWEB)
Mark Rhode
2005-04-01
. Due to the composition of coal, particulate matter is also a by-product of coal combustion. Modern day utility boilers are usually fitted with electrostatic precipitators to aid in the collection of particulate matter. Although extremely efficient, these devices are sensitive to rapid changes in inlet mass concentration as well as total mass loading. Traditionally, utility boilers are equipped with devices known as sootblowers, which use, steam, water or air to dislodge and clean the surfaces within the boiler and are operated based upon established rule or operator's judgment. Poor sootblowing regimes can influence particulate mass loading to the electrostatic precipitators. The project applied a neural network intelligent sootblowing system in conjunction with state-of-the-art controls and instruments to optimize the operation of a utility boiler and systematically control boiler slagging/fouling. This optimization process targeted reduction of NOx of 30%, improved efficiency of 2% and a reduction in opacity of 5%. The neural network system proved to be a non-invasive system which can readily be adapted to virtually any utility boiler. Specific conclusions from this neural network application are listed below. These conclusions should be used in conjunction with the specific details provided in the technical discussions of this report to develop a thorough understanding of the process.
Distorted Character Recognition Via An Associative Neural Network
Messner, Richard A.; Szu, Harold H.
1987-03-01
The purpose of this paper is two-fold. First, it is intended to provide some preliminary results of a character recognition scheme which has foundations in on-going neural network architecture modeling, and secondly, to apply some of the neural network results in a real application area where thirty years of effort has had little effect on providing the machine an ability to recognize distorted objects within the same object class. It is the author's belief that the time is ripe to start applying in ernest the results of over twenty years of effort in neural modeling to some of the more difficult problems which seem so hard to solve by conventional means. The character recognition scheme proposed utilizes a preprocessing stage which performs a 2-dimensional Walsh transform of an input cartesian image field, then sequency filters this spectrum into three feature bands. Various features are then extracted and organized into three sets of feature vectors. These vector patterns that are stored and recalled associatively. Two possible associative neural memory models are proposed for further investigation. The first being an outer-product linear matrix associative memory with a threshold function controlling the strength of the output pattern (similar to Kohonen's crosscorrelation approach [1]). The second approach is based upon a modified version of Grossberg's neural architecture [2] which provides better self-organizing properties due to its adaptive nature. Preliminary results of the sequency filtering and feature extraction preprocessing stage and discussion about the use of the proposed neural architectures is included.
Phase Diagram of Spiking Neural Networks
Directory of Open Access Journals (Sweden)
Hamed eSeyed-Allaei
2015-03-01
Full Text Available In computer simulations of spiking neural networks, often it is assumed that every two neurons of the network are connected by a probablilty of 2%, 20% of neurons are inhibitory and 80% are excitatory. These common values are based on experiments, observations. but here, I take a different perspective, inspired by evolution. I simulate many networks, each with a different set of parameters, and then I try to figure out what makes the common values desirable by nature. Networks which are configured according to the common values, have the best dynamic range in response to an impulse and their dynamic range is more robust in respect to synaptic weights. In fact, evolution has favored networks of best dynamic range. I present a phase diagram that shows the dynamic ranges of different networks of different parameteres. This phase diagram gives an insight into the space of parameters -- excitatory to inhibitory ratio, sparseness of connections and synaptic weights. It may serve as a guideline to decide about the values of parameters in a simulation of spiking neural network.
2016-05-31
foundations for, integration of predictive neural networks into Bayesian networks as a means of generating probability distribution functions and...using a neural network and secondly, fusing this and other types of sensor output into a single probabilistic evaluation of multiple sensor outputs...Integration of Neural Networks with Bayesian Networks for Data Fusion and Predictive Modeling The views, opinions and/or findings contained in this
Fuzzy logic and neural networks basic concepts & application
Alavala, Chennakesava R
2008-01-01
About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank
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
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
Electrokinetic confinement of axonal growth for dynamically configurable neural networks
Honegger, Thibault; Scott, Mark A.; Yanik, Mehmet F.; Voldman, Joel
2013-01-01
Axons in the developing nervous system are directed via guidance cues, whose expression varies both spatially and temporally, to create functional neural circuits. Existing methods to create patterns of neural connectivity in vitro use only static geometries, and are unable to dynamically alter the guidance cues imparted on the cells. We introduce the use of AC electrokinetics to dynamically control axonal growth in cultured rat hippocampal neurons. We find that the application of modest voltages at frequencies on the order of 105 Hz can cause developing axons to be stopped adjacent to the electrodes while axons away from the electric fields exhibit uninhibited growth. By switching electrodes on or off, we can reversibly inhibit or permit axon passage across the electrodes. Our models suggest that dielectrophoresis is the causative AC electrokinetic effect. We make use of our dynamic control over axon elongation to create an axon-diode via an axon-lock system that consists of a pair of electrode `gates' that either permit or prevent axons from passing through. Finally, we developed a neural circuit consisting of three populations of neurons, separated by three axon-locks to demonstrate the assembly of a functional, engineered neural network. Action potential recordings demonstrate that the AC electrokinetic effect does not harm axons, and Ca2+ imaging demonstrated the unidirectional nature of the synaptic connections. AC electrokinetic confinement of axonal growth has potential for creating configurable, directional neural networks. PMID:23314575
Mirbagheri, Seyed Ahmad; Bagheri, Majid; Boudaghpour, Siamak; Ehteshami, Majid; Bagheri, Zahra
2015-01-01
Treatment process models are efficient tools to assure proper operation and better control of wastewater treatment systems. The current research was an effort to evaluate performance of a submerged membrane bioreactor (SMBR) treating combined municipal and industrial wastewater and to simulate effluent quality parameters of the SMBR using a radial basis function artificial neural network (RBFANN). The results showed that the treatment efficiencies increase and hydraulic retention time (HRT) decreases for combined wastewater compared with municipal and industrial wastewaters. The BOD, COD, [Formula: see text] and total phosphorous (TP) removal efficiencies for combined wastewater at HRT of 7 hours were 96.9%, 96%, 96.7% and 92%, respectively. As desirable criteria for treating wastewater, the TBOD/TP ratio increased, the BOD and COD concentrations decreased to 700 and 1000 mg/L, respectively and the BOD/COD ratio was about 0.5 for combined wastewater. The training procedures of the RBFANN models were successful for all predicted components. The train and test models showed an almost perfect match between the experimental and predicted values of effluent BOD, COD, [Formula: see text] and TP. The coefficient of determination (R(2)) values were higher than 0.98 and root mean squared error (RMSE) values did not exceed 7% for train and test models.
Guo, Zhiqiang; Wang, Huaiqing; Yang, Jie; Miller, David J
2015-01-01
In this paper, we propose and implement a hybrid model combining two-directional two-dimensional principal component analysis ((2D)2PCA) and a Radial Basis Function Neural Network (RBFNN) to forecast stock market behavior. First, 36 stock market technical variables are selected as the input features, and a sliding window is used to obtain the input data of the model. Next, (2D)2PCA is utilized to reduce the dimension of the data and extract its intrinsic features. Finally, an RBFNN accepts the data processed by (2D)2PCA to forecast the next day's stock price or movement. The proposed model is used on the Shanghai stock market index, and the experiments show that the model achieves a good level of fitness. The proposed model is then compared with one that uses the traditional dimension reduction method principal component analysis (PCA) and independent component analysis (ICA). The empirical results show that the proposed model outperforms the PCA-based model, as well as alternative models based on ICA and on the multilayer perceptron.
Directory of Open Access Journals (Sweden)
Zhiqiang Guo
Full Text Available In this paper, we propose and implement a hybrid model combining two-directional two-dimensional principal component analysis ((2D2PCA and a Radial Basis Function Neural Network (RBFNN to forecast stock market behavior. First, 36 stock market technical variables are selected as the input features, and a sliding window is used to obtain the input data of the model. Next, (2D2PCA is utilized to reduce the dimension of the data and extract its intrinsic features. Finally, an RBFNN accepts the data processed by (2D2PCA to forecast the next day's stock price or movement. The proposed model is used on the Shanghai stock market index, and the experiments show that the model achieves a good level of fitness. The proposed model is then compared with one that uses the traditional dimension reduction method principal component analysis (PCA and independent component analysis (ICA. The empirical results show that the proposed model outperforms the PCA-based model, as well as alternative models based on ICA and on the multilayer perceptron.
A Projection Neural Network for Constrained Quadratic Minimax Optimization.
Liu, Qingshan; Wang, Jun
2015-11-01
This paper presents a projection neural network described by a dynamic system for solving constrained quadratic minimax programming problems. Sufficient conditions based on a linear matrix inequality are provided for global convergence of the proposed neural network. Compared with some of the existing neural networks for quadratic minimax optimization, the proposed neural network in this paper is capable of solving more general constrained quadratic minimax optimization problems, and the designed neural network does not include any parameter. Moreover, the neural network has lower model complexities, the number of state variables of which is equal to that of the dimension of the optimization problems. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural network.
Investment Valuation Analysis with Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Hüseyin İNCE
2017-07-01
Full Text Available This paper shows that discounted cash flow and net present value, which are traditional investment valuation models, can be combined with artificial neural network model forecasting. The main inputs for the valuation models, such as revenue, costs, capital expenditure, and their growth rates, are heavily related to sector dynamics and macroeconomics. The growth rates of those inputs are related to inflation and exchange rates. Therefore, predicting inflation and exchange rates is a critical issue for the valuation output. In this paper, the Turkish economy’s inflation rate and the exchange rate of USD/TRY are forecast by artificial neural networks and implemented to the discounted cash flow model. Finally, the results are benchmarked with conventional practices.
Evaluating neural networks and artificial intelligence systems
Alberts, David S.
1994-02-01
Systems have no intrinsic value in and of themselves, but rather derive value from the contributions they make to the missions, decisions, and tasks they are intended to support. The estimation of the cost-effectiveness of systems is a prerequisite for rational planning, budgeting, and investment documents. Neural network and expert system applications, although similar in their incorporation of a significant amount of decision-making capability, differ from each other in ways that affect the manner in which they can be evaluated. Both these types of systems are, by definition, evolutionary systems, which also impacts their evaluation. This paper discusses key aspects of neural network and expert system applications and their impact on the evaluation process. A practical approach or methodology for evaluating a certain class of expert systems that are particularly difficult to measure using traditional evaluation approaches is presented.
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...
Hierarchical Neural Network Structures for Phoneme Recognition
Vasquez, Daniel; Minker, Wolfgang
2013-01-01
In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.
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.
Adaptive thresholds for neural networks with synaptic noise.
Bollé, D; Heylen, R
2007-08-01
The inclusion of a macroscopic adaptive threshold is studied for the retrieval dynamics of both layered feedforward and fully connected neural network models with synaptic noise. These two types of architectures require a different method to be solved numerically. In both cases it is shown that, if the threshold is chosen appropriately as a function of the cross-talk noise and of the activity of the stored patterns, adapting itself automatically in the course of the recall process, an autonomous functioning of the network is guaranteed. This self-control mechanism considerably improves the quality of retrieval, in particular the storage capacity, the basins of attraction and the mutual information content.
Neural Network Solves "Traveling-Salesman" Problem
Thakoor, Anilkumar P.; Moopenn, Alexander W.
1990-01-01
Experimental electronic neural network solves "traveling-salesman" problem. Plans round trip of minimum distance among N cities, visiting every city once and only once (without backtracking). This problem is paradigm of many problems of global optimization (e.g., routing or allocation of resources) occuring in industry, business, and government. Applied to large number of cities (or resources), circuits of this kind expected to solve problem faster and more cheaply.
Learning in Neural Networks: VLSI Implementation Strategies
Duong, Tuan Anh
1995-01-01
Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.
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...
Deep Learning in Neural Networks: An Overview
Schmidhuber, Juergen
2014-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpr...
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
Artificial neural network cardiopulmonary modeling and diagnosis
Kangas, Lars J.; Keller, Paul E.
1997-01-01
The present invention is a method of diagnosing a cardiopulmonary condition in an individual by comparing data from a progressive multi-stage test for the individual to a non-linear multi-variate model, preferably a recurrent artificial neural network having sensor fusion. The present invention relies on a cardiovascular model developed from physiological measurements of an individual. Any differences between the modeled parameters and the parameters of an individual at a given time are used for diagnosis.
Identifying Tracks Duplicates via Neural Network
Sunjerga, Antonio; CERN. Geneva. EP Department
2017-01-01
The goal of the project is to study feasibility of state of the art machine learning techniques in track reconstruction. Machine learning techniques provide promising ways to speed up the pattern recognition of tracks by adding more intelligence in the algorithms. Implementation of neural network to process of track duplicates identifying will be discussed. Different approaches are shown and results are compared to method that is currently in use.
Some structural determinants of Pavlovian conditioning in artificial neural networks.
Sánchez, José M; Galeazzi, Juan M; Burgos, José E
2010-05-01
This paper investigates the possible role of neuroanatomical features in Pavlovian conditioning, via computer simulations with layered, feedforward artificial neural networks. The networks' structure and functioning are described by a strongly bottom-up model that takes into account the roles of hippocampal and dopaminergic systems in conditioning. Neuroanatomical features were simulated as generic structural or architectural features of neural networks. We focused on the number of units per hidden layer and connectivity. The effect of the number of units per hidden layer was investigated through simulations of resistance to extinction in fully connected networks. Large networks were more resistant to extinction than small networks, a stochastic effect of the asynchronous random procedure used in the simulator to update activations and weights. These networks did not simulate second-order conditioning because weight competition prevented conditioning to a stimulus after conditioning to another. Partially connected networks simulated second-order conditioning and devaluation of the second-order stimulus after extinction of a similar first-order stimulus. Similar stimuli were simulated as nonorthogonal input-vectors. Copyright (c) 2009 Elsevier B.V. All rights reserved.
Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen
2013-02-01
This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.
Multilingual Text Detection with Nonlinear Neural Network
Directory of Open Access Journals (Sweden)
Lin Li
2015-01-01
Full Text Available Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work.
Forecasting Energy Commodity Prices Using Neural Networks
Directory of Open Access Journals (Sweden)
Massimo Panella
2012-01-01
Full Text Available A new machine learning approach for price modeling is proposed. The use of neural networks as an advanced signal processing tool may be successfully used to model and forecast energy commodity prices, such as crude oil, coal, natural gas, and electricity prices. Energy commodities have shown explosive growth in the last decade. They have become a new asset class used also for investment purposes. This creates a huge demand for better modeling as what occurred in the stock markets in the 1970s. Their price behavior presents unique features causing complex dynamics whose prediction is regarded as a challenging task. The use of a Mixture of Gaussian neural network may provide significant improvements with respect to other well-known models. We propose a computationally efficient learning of this neural network using the maximum likelihood estimation approach to calibrate the parameters. The optimal model is identified using a hierarchical constructive procedure that progressively increases the model complexity. Extensive computer simulations validate the proposed approach and provide an accurate description of commodities prices dynamics.
Flood estimation: a neural network approach
Energy Technology Data Exchange (ETDEWEB)
Swain, P.C.; Seshachalam, C.; Umamahesh, N.V. [Regional Engineering Coll., Warangal (India). Water and Environment Div.
2000-07-01
The artificial neural network (ANN) approach described in this study aims at predicting the flood flow into a reservoir. This differs from the traditional methods of flow prediction in the sense that it belongs to a class of data driven approaches, where as the traditional methods are model driven. Physical processes influencing the occurrences of streamflow in a river are highly complex, and are very difficult to be modelled by available statistical or deterministic models. ANNs provide model free solutions and hence can be expected to be appropriate in these conditions. Non-linearity, adaptivity, evidential response and fault tolerance are additional properties and capabilities of the neural networks. This paper highlights the applicability of neural networks for predicting daily flood flow taking the Hirakud reservoir on river Mahanadi in Orissa, India as the case study. The correlation between the observed and predicted flows and the relative error are considered to measure the performance of the model. The correlation between the observed and the modelled flows are computed to be 0.9467 in testing phase of the model. (orig.)
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.
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.
Artificial neural network applications in ionospheric studies
Directory of Open Access Journals (Sweden)
L. R. Cander
1998-06-01
Full Text Available The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC. Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.
Improved Extension Neural Network and Its Applications
Directory of Open Access Journals (Sweden)
Yu Zhou
2014-01-01
Full Text Available Extension neural network (ENN is a new neural network that is a combination of extension theory and artificial neural network (ANN. The learning algorithm of ENN is based on supervised learning algorithm. One of important issues in the field of classification and recognition of ENN is how to achieve the best possible classifier with a small number of labeled training data. Training data selection is an effective approach to solve this issue. In this work, in order to improve the supervised learning performance and expand the engineering application range of ENN, we use a novel data selection method based on shadowed sets to refine the training data set of ENN. Firstly, we use clustering algorithm to label the data and induce shadowed sets. Then, in the framework of shadowed sets, the samples located around each cluster centers (core data and the borders between clusters (boundary data are selected as training data. Lastly, we use selected data to train ENN. Compared with traditional ENN, the proposed improved ENN (IENN has a better performance. Moreover, IENN is independent of the supervised learning algorithms and initial labeled data. Experimental results verify the effectiveness and applicability of our proposed work.
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.
A neural network model for texture discrimination.
Xing, J; Gerstein, G L
1993-01-01
A model of texture discrimination in visual cortex was built using a feedforward network with lateral interactions among relatively realistic spiking neural elements. The elements have various membrane currents, equilibrium potentials and time constants, with action potentials and synapses. The model is derived from the modified programs of MacGregor (1987). Gabor-like filters are applied to overlapping regions in the original image; the neural network with lateral excitatory and inhibitory interactions then compares and adjusts the Gabor amplitudes in order to produce the actual texture discrimination. Finally, a combination layer selects and groups various representations in the output of the network to form the final transformed image material. We show that both texture segmentation and detection of texture boundaries can be represented in the firing activity of such a network for a wide variety of synthetic to natural images. Performance details depend most strongly on the global balance of strengths of the excitatory and inhibitory lateral interconnections. The spatial distribution of lateral connective strengths has relatively little effect. Detailed temporal firing activities of single elements in the lateral connected network were examined under various stimulus conditions. Results show (as in area 17 of cortex) that a single element's response to image features local to its receptive field can be altered by changes in the global context.
Categorization in neural networks and prosopagnosia
Virasoro, M. A.
1989-12-01
Prosopagnosia is a syndrome characterized by a generalized difficulty to visually recognize individual patterns among those that are similar, and can therefore be said to belong to the same category. I suggest that the existence of this disfunction may be an important clue for understanding the categorization process in the brain. In this direction the performance of neural networks under random destruction of synapses is analysed. It is found that in almost every network that stores correlated patterns the coding of the discriminating details between individuals inside a class is more sensitive to noise or to random destruction than the coding that distinguishes between classes. It follows that a process of death and/or deterioration at an intermediate level of intensity, even if it acts randomly on the network may lead to a malfunctioning of the network that resembles prosopagnosia.