By Topic

IEEE Transactions on Neural Networks

Issue 1 • Jan. 1995

Filter Results

Displaying Results 1 - 25 of 33
  • Locally excitatory globally inhibitory oscillator networks

    Publication Year: 1995, Page(s):283 - 286
    Cited by:  Papers (135)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    A novel class of locally excitatory, globally inhibitory oscillator networks (LEGION) is proposed and investigated. The model of each oscillator corresponds to a standard relaxation oscillator with two time scales. In the network, an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing other oscillators from jumping up. Compute... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of a quasi-Newton method in a feedforward neural network construction algorithm

    Publication Year: 1995, Page(s):273 - 277
    Cited by:  Papers (104)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    This paper describes an algorithm for constructing a single hidden layer feedforward neural network. A distinguishing feature of this algorithm is that it uses the quasi-Newton method to minimize the sequence of error functions associated with the growing network. Experimental results indicate that the algorithm is very efficient and robust. The algorithm was tested on two test problems. The first... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Back-propagation network and its configuration for blood vessel detection in angiograms

    Publication Year: 1995, Page(s):64 - 72
    Cited by:  Papers (58)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (808 KB)

    A neural-network classifier for detecting vascular structures in angiograms was developed. The classifier consisted of a multilayer feedforward network window in which the center pixel was classified using gray-scale information within the window. The network was trained by using the backpropagation algorithm with the momentum term. Based on this image segmentation problem, the effect of changing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive learning method in self-organizing map for edge preserving vector quantization

    Publication Year: 1995, Page(s):278 - 280
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    The Kohonen's self-organizing map algorithm for vector quantization of images is modified to reduce the edge degradation in the coded image. The learning procedure is performed by adaptive learning rates that are determined according to the image block activity. The simulation result of 4×4 vector quantization for 512×512 image coding demonstrates the feasibility of the proposed method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High speed paper currency recognition by neural networks

    Publication Year: 1995, Page(s):73 - 77
    Cited by:  Papers (46)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (480 KB)

    In this paper a new technique is proposed to improve the recognition ability and the transaction speed to classify the Japanese and US paper currency. Two types of data sets, time series data and Fourier power spectra, are used in this study. In both cases, they are directly used as inputs to the neural network. Furthermore, we also refer a new evaluation method of recognition ability. Meanwhile, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal adaptive k-means algorithm with dynamic adjustment of learning rate

    Publication Year: 1995, Page(s):157 - 169
    Cited by:  Papers (103)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1088 KB)

    Adaptive k-means clustering algorithms have been used in several artificial neural network architectures, such as radial basis function networks or feature-map classifiers, for a competitive partitioning of the input domain. This paper presents an enhancement of the traditional k-means algorithm. It approximates an optimal clustering solution with an efficient adaptive learning rate, which renders... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A single-iteration threshold Hamming network

    Publication Year: 1995, Page(s):261 - 266
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    We analyze in detail the performance of a Hamming network classifying inputs that are distorted versions of one of its m stored memory patterns, each being a binary vector of length n. It is shown that the activation function of the memory neurons in the original Hamming network may be replaced by a simple threshold function. By judiciously determining the threshold value, the “winner-take-a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Canonical piecewise-linear networks

    Publication Year: 1995, Page(s):43 - 50
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (852 KB)

    In this paper, mapping networks will be considered from the viewpoint of the piecewise-linear (PWL) approximation. The so-called canonical representation plays a kernel role in the PWL representation theory. While this theory has been researched intensively in the contents of mathematics and circuit simulations, little has been seen in the research area about the theoretical aspect of neural netwo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Limitations of neural networks for solving traveling salesman problems

    Publication Year: 1995, Page(s):280 - 282
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    Feedback neural networks enjoy considerable popularity as a means of approximately solving combinatorial optimization problems. It is now well established how to map problems onto networks so that invalid solutions are never found. It is not as clear how the networks' solutions compare in terms of quality with those obtained using other optimization techniques; such issues are addressed in this pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust principal component analysis by self-organizing rules based on statistical physics approach

    Publication Year: 1995, Page(s):131 - 143
    Cited by:  Papers (95)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1184 KB)

    This paper applies statistical physics to the problem of robust principal component analysis (PCA). The commonly used PCA learning rules are first related to energy functions. These functions are generalized by adding a binary decision field with a given prior distribution so that outliers in the data are dealt with explicitly in order to make PCA robust. Each of the generalized energy functions i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Asymptotic level density in topological feature maps

    Publication Year: 1995, Page(s):230 - 236
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    The Kohonen algorithm entails a topology conserving mapping of an input pattern space X⊂Rn characterized by an a priori probability distribution P(x), x∈X, onto a discrete lattice of neurons r with virtual positions wr∈X. Extending results obtained by Ritter (1991) the authors show in the one-dimensional case for an arbitrary monotonously decreasing neighborhood... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Process modeling with the regression network

    Publication Year: 1995, Page(s):78 - 93
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1536 KB)

    A new connectionist network topology called the regression network is proposed. The structural and underlying mathematical features of the regression network are investigated. Emphasis is placed on the intricacies of the optimization process for the regression network and some measures to alleviate these difficulties of optimization are proposed and investigated. The ability of the regression netw... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision-based neural networks with signal/image classification applications

    Publication Year: 1995, Page(s):170 - 181
    Cited by:  Papers (94)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1132 KB)

    Supervised learning networks based on a decision-based formulation are explored. More specifically, a decision-based neural network (DBNN) is proposed, which combines the perceptron-like learning rule and hierarchical nonlinear network structure. The decision-based mutual training can be applied to both static and temporal pattern recognition problems. For static pattern recognition, two hierarchi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The transversal imager: a photonic neurochip with programmable synaptic weights

    Publication Year: 1995, Page(s):248 - 251
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    A photonic neural processor implemented in NMOS/CCD integrated circuit technology is described. The processor performs outer-product processing utilizing optical input of the synaptic weights and electrical input of the state vector, or, visa versa. The performance of the 32-neuron, 1024-synapse processor is presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis and synthesis of a class of discrete-time neural networks with multilevel threshold neurons

    Publication Year: 1995, Page(s):105 - 116
    Cited by:  Papers (31)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1016 KB)

    In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time neural networks with multilevel threshold neurons is developed. A qualitative analysis and a synthesis procedure for the class of neural networks considered constitute the principal contributions of this paper. The applicability of the present class of neural networks is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Existence and uniqueness results for neural network approximations

    Publication Year: 1995, Page(s):2 - 13
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (916 KB)

    Some approximation theoretic questions concerning a certain class of neural networks are considered. The networks considered are single input, single output, single hidden layer, feedforward neural networks with continuous sigmoidal activation functions, no input weights but with hidden layer thresholds and output layer weights. Specifically, questions of existence and uniqueness of best approxima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neighborhood sequential and random training techniques for CMAC

    Publication Year: 1995, Page(s):196 - 202
    Cited by:  Papers (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    An adaptive control algorithm based on Albus' CMAC (Cerebellar Model Articulation Controller) was studied with emphasis on how to train CMAC systems. Two training techniques-neighborhood sequential training and random training, have been devised. These techniques were used to generate mathematical functions, and both methods successfully circumvented the training interference resulting from CMAC's... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning capability assessment and feature space optimization for higher-order neural networks

    Publication Year: 1995, Page(s):267 - 272
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    A technique for evaluating the learning capability and optimizing the feature space of a class of higher-order neural networks is presented. It is shown that supervised learning can be posed as an optimization problem in which inequality constraints are used to code the information contained in the training patterns and to specify the degree of accuracy expected from the neural network. The approa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy multi-layer perceptron, inferencing and rule generation

    Publication Year: 1995, Page(s):51 - 63
    Cited by:  Papers (93)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1056 KB)

    A connectionist expert system model, based on a fuzzy version of the multilayer perceptron developed by the authors, is proposed. It infers the output class membership value(s) of an input pattern and also generates a measure of certainty expressing confidence in the decision. The model is capable of querying the user for the more important input feature information, if and when required, in case ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Diagonal recurrent neural networks for dynamic systems control

    Publication Year: 1995, Page(s):144 - 156
    Cited by:  Papers (439)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (880 KB)

    A new neural paradigm called diagonal recurrent neural network (DRNN) is presented. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer, and the hidden layer comprises self-recurrent neurons. Two DRNN's are utilized in a control system, one as an identifier called diagonal recurrent neuroidentifier (DRNI) and the other as a controller ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analog optimization with Wong's stochastic neural network

    Publication Year: 1995, Page(s):258 - 260
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    We describe E. Wong's stochastic neural network (1989) and show that it can be used, in principle, to perform analog optimization. The optimization dynamics are analogous to those of simulated annealing. To show this, we use the theory developed in Holley and Stroock (1988) for the continuous-time simulated annealing process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer

    Publication Year: 1995, Page(s):31 - 42
    Cited by:  Papers (98)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1016 KB)

    Multilayer perceptrons are successfully used in an increasing number of nonlinear signal processing applications. The backpropagation learning algorithm, or variations hereof, is the standard method applied to the nonlinear optimization problem of adjusting the weights in the network in order to minimize a given cost function. However, backpropagation as a steepest descent approach is too slow for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving the performance of Kanerva's associate memory

    Publication Year: 1995, Page(s):125 - 130
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    A parallel associative memory first proposed by Kanerva (1988) is discussed. The major appeal of this memory is its ability to be trained very rapidly. A discrepancy between Kanerva's theoretical calculation of capacity and the actual capacity is demonstrated experimentally and a corrected theory is offered. A modified method of reading from memory is suggested which results in a capacity nearly t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Random noise effects in pulse-mode digital multilayer neural networks

    Publication Year: 1995, Page(s):220 - 229
    Cited by:  Papers (27)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (804 KB)

    A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The geometrical learning of binary neural networks

    Publication Year: 1995, Page(s):237 - 247
    Cited by:  Papers (69)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (900 KB)

    In this paper, the learning algorithm called expand-and-truncate learning (ETL) is proposed to train multilayer binary neural networks (BNN) with guaranteed convergence for any binary-to-binary mapping. The most significant contribution of this paper is the development of a learning algorithm for three-layer BNN which guarantees the convergence, automatically determining a required number of neuro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Transactions on Neural Networks is devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware.

 

This Transactions ceased production in 2011. The current retitled publication is IEEE Transactions on Neural Networks and Learning Systems.

Full Aims & Scope