1989 First IEE International Conference on Artificial Neural Networks, (Conf. Publ. No. 313)

16-18 Oct. 1989

Filter Results

Displaying Results 1 - 25 of 87
  • On the significance of internal representations in neural networks

    Publication Year: 1989
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (30 KB)

    Summary form only given. For a straightforward materialization of internal representations, semantic networks are suggested. In their original form they comprise a graph structure with nodes and links. The nodes may stand for items or concepts (sets of attributes), whereas the links usually indicate relations. In view of the contemporary neurophysiological data, such a degree of specificity and sp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimating hidden units for two-layer perceptrons

    Publication Year: 1989, Page(s):120 - 124
    Cited by:  Papers (25)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (241 KB)

    A method of estimating the number of hidden units required by a two-layer perceptron learning binary mappings using back propagation of error signals is presented. In order to obtain an estimate of the number of hidden units for a fully connected net with n output units, it is necessary to obtain an estimate of the number of 'conflicts' contained in the individual binary responses that must be lea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Diffusion learning for the multilayer perceptron

    Publication Year: 1989, Page(s):390 - 394
    Cited by:  Papers (5)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (191 KB)

    A method of nonconvex optimisation based on simulating diffusion processes is discussed and applied to learning in the multilayer perceptron. It is compared with simulated annealing and back propagation of error as an optimisation learning tool. Results indicate significant improvement on these traditional learning methods. The method may be easily implemented in existing hardware.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of neural network structures for practical application in a pattern recognition environment

    Publication Year: 1989, Page(s):378 - 382
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (272 KB)

    The recognition performance of three different types of neural network involving differing structures and different learning algorithms is compared. The networks are the probabilistic logic node, a neuron configuration using a back error propagation algorithm, and the ART1 neural model. The potential of different neural network types in a common practical recognition task is demonstrated and it is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image processing with optimum neural networks

    Publication Year: 1989, Page(s):374 - 377
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (384 KB)

    Although neurons in intermediate layers (hidden units) are very important components of most neural networks, there is a lack of general rules specifying how many hidden layers and how many hidden units per layer should be used to achieve optimum performance of a network. This lack of rules has its roots in the difficulty in judging the performance of the hidden units. The most widely used trainin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matching of attributed and nonattributed graphs by use of a Boltzmann machine algorithm

    Publication Year: 1989, Page(s):369 - 373
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (224 KB)

    The paper deals with the task of solving the pure topological subgraph isomorphism problem and with the finding of a best relational matching subgraph to a given reference graph in an image graph with respect to both graphs' attributes. In both cases, a combination of a simulated annealing strategy and of a Hungarian method algorithm is used. This combined strategy performs faster than the relaxat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Can perceptrons find Lyapunov functions?-an algorithmic approach to systems stability

    Publication Year: 1989, Page(s):364 - 368
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (188 KB)

    A machine implementable algorithm is developed for determining Lyapunov functions. The method is based on the perceptron algorithm and so is easily implemented on a neural network View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural net for processing of stationary signals in the auditory system

    Publication Year: 1989, Page(s):287 - 291
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (332 KB)

    In the auditory domain, since the first work by Rose and colleagues, it is well-known that responses in single auditory nerve fibers are phase-locked to the frequency components of an acoustic stimulation. The present authors describe a neural net which intimately links geographical and temporal aspects of neural coding. It is built from: a mathematical property concerning crossed correlations bet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training networks with discontinuous activation functions

    Publication Year: 1989, Page(s):361 - 363
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (168 KB)

    This paper presents a learning algorithm which may be used to train networks whose neurons may have discontinuous or nondifferentiable activation functions. The algorithm has been demonstrated using several different neuron activation functions. Although it shares several features with the error back-propagation algorithm, the heuristic derivation presented does not appeal to the highly mathematic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying and discriminating temporal events with connectionist language users

    Publication Year: 1989, Page(s):284 - 286
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (188 KB)

    Connectionist learning algorithms related to back-propagation have proven so effective that recent work has seriously considered the possibility of developing systems which learn and use natural language rather than processing it. This approach is termed the study of `connectionist language users'. The connectionist language user paradigm is applied to several studies of the perception, processing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Equalisation using neural networks

    Publication Year: 1989, Page(s):356 - 360
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (220 KB)

    Neural networks offer a number of advantages over other architectures: they are capable of generalisation, and because of their strong-interconnectivity, they are capable of offering real-time solutions to complex optimisation problems. The authors have applied a multilayer feed-forward network of perceptrons to the problem of equalisation in digital communication systems. In the absence of rigoro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structured neural networks for Markovian processes

    Publication Year: 1989, Page(s):319 - 323
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (236 KB)

    A multi-layer perceptron (MLP) containing fixed structured regions consisting of delay lines and feedback units is stable under error-backpropagation. It is proposed that learning with a structured network succeeds where a fully connected, layered network fails. An example is presented: the input to the network is a time varying signal; when a hidden Markov model is used as input, the network lear... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extension of the Hamming neural network to a multilayer architecture for optical implementation

    Publication Year: 1989, Page(s):280 - 283
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (188 KB)

    Examines how the Hamming net can be extended to a three layer architecture by means of the matched filter formalism. When the convergence parameters are set below a defined upper limit the net always converges to the correct pattern and so offers a definite advantage over the Hopfield net. Moreover, the Hamming convergence parameters can be made to affect the threshold offset rather than its slope... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An implementation of fully analogue sum-of-product neural models in VLSI

    Publication Year: 1989, Page(s):52 - 56
    Cited by:  Papers (6)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (232 KB)

    Neural networks that use digital or partly digital processing units have a restricted set of applications, and also are constrained by the set of learning rules that can be used with them. Analogue networks have a greater flexibility in their learning algorithms and a larger domain of problems which they can solve. The flexibility of an analogue output capability can also be used to give an idea o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the training and the convergence of brain-state-in-a-box neural networks

    Publication Year: 1989, Page(s):247 - 251
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (324 KB)

    It is the aim of the paper to contribute to the understanding and applicability of brain-state-in-a-box neural networks. It is shown how asymmetric brain-state-in-a-box neural networks achieve a multiple objective optimization, generalizing the `energy'-interpretation of symmetric neural networks. It is therefore expected that asymmetric neural networks will have interesting applications once the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An example of back propagation: diagnosis of dyspepsia

    Publication Year: 1989, Page(s):332 - 336
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (200 KB)

    The authors attempt to apply the back-propagation method (BP), described by Rumelhart and McClelland (1986), to dyspepsia diagnosis. In particular the program utilizes the method with adaptive learning parameters taken from the method adopted by Vogl (1988). The major aim is to identify patients who are suspected of having a neoplastic disease and need further diagnostic testing. The long term aim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning with inference cells

    Publication Year: 1989, Page(s):399 - 403
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (192 KB)

    This paper introduces a learning method for neural nets using logic nodes. This learning method is based on very simple rules which are local to each cell. It is based on an inference mechanism associated with each cell and a transmitting/receiving process of inter-cell message passing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical flow estimation by using the artificial neural network under multi-layers

    Publication Year: 1989, Page(s):76 - 80
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (332 KB)

    A Hopfield model for computing optical flow is presented. A set of features describing the local intensity structure along the principal directions is used to measure the matching between the two local neighborhoods in the successive frames. The energy function can be derived based on the match measure and regularized by adding the Tikhonov stabilizer of the smoothness constraints. This energy fun... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of artificial neural network techniques to low bit-rate speech coding

    Publication Year: 1989, Page(s):100 - 104
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (200 KB)

    Research has been undertaken to investigate the use of artificial neural network (ANN) techniques to improve the performance of a low bit-rate vector transform coder. Considerable improvements in the perceptual quality of the coded speech have been obtained. New ANN-based methods for vector quantiser (VQ) design and for the adaptive updating of VQ code book are introduced for use in speech coding ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linked assembly of neural networks to solve the interconnection problem

    Publication Year: 1989, Page(s):216 - 220
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (344 KB)

    In order to reduce the complexity of training a neural network, partitioning of the problem is introduced to facilitate the identification of smaller and, if possible, replicable networks which are more readily trained. An interactive software system for the linked assembly of these neural networks (ASLANN) has been developed and is used to generate the final network. To demonstrate this technique... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive radial basis function nonlinearities, and the problem of generalisation

    Publication Year: 1989, Page(s):171 - 175
    Cited by:  Papers (34)  |  Patents (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (348 KB)

    The author and D.S. Broomhead developed (1988) the opinion that most current feedforward layered neural networks perform a curve fitting operation in a high-dimensional space. To create the analogy, it was necessary to generalise earlier papers' assumptions, and so a mechanism for choosing radial basis functions was needed. The method involves optimisation. It is concluded that nonlinear optimisat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of the Kohonen and multiedit neural net learning algorithms

    Publication Year: 1989, Page(s):7 - 11
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (280 KB)

    This paper presents a comparative evaluation of the multiedit/condensing and Kohonen neural net learning algorithms using a speaker-independent speech recognition problem as a test vehicle. Both approaches attempt to cover the subspaces associated with respective pattern classes by a small number of reference vectors for subsequent nearest neighbour classification of unknown patterns. Several impo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A continuously adaptable artificial neural network

    Publication Year: 1989, Page(s):351 - 355
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (236 KB)

    Describes the development of an artificial neuron based loosely on evidence from natural neurons. The organization of these neurons into an artificial network, termed a differentiator, is discussed. Simulation results are presented which demonstrate the ability of the network to categorise noise-corrupted input patterns and adapt to changing input patterns View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical character recognition using artificial neural networks

    Publication Year: 1989, Page(s):191 - 195
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (304 KB)

    Optical character recognition is examined to find a general framework by which it can be realized. A hierarchical `cone' with feature extraction layers of increasing sophistication is described. The system, unlike the artificial neural net examples in the literature, does not use one network only. Allowing recognition to take place in parallel over different representations of the same symbol intr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamics of neural networks with restricted-range connections

    Publication Year: 1989, Page(s):315 - 318
    IEEE is not the copyright holder of this material | Click to expandAbstract |PDF file iconPDF (228 KB)

    The author analyses the neural networks in which the connection range scales sublinearly with the network diameter. Combining this with randomly sparse connectivity leads to fully functional networks with electronically or biologically realisable wiring requirements. Evolution equations for semi-local measures of similarity to the exemplars are derived. Their solutions are analysed to study the pr... View full abstract»

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