Scheduled System Maintenance
On Tuesday, September 26, IEEE Xplore will undergo scheduled maintenance from 1:00-4:00 PM ET.
During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

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
  • 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.
  • Neural network architectures for associative memory

    Publication Year: 1989, Page(s):17 - 22
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (364 KB)

    This paper identifies optimal strategies available for the computation of synaptic weights in both auto- and hetero-associative networks. An iterative algorithm is proposed to train fully-connected feedback networks and it is shown that the recall performance can be predicted without recourse to protracted simulation studies. More importantly, the vast superiority of Hamming-type networks for bina... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organization based on the second maximum entropy principle

    Publication Year: 1989, Page(s):12 - 16
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (192 KB)

    The article formulates an optimal mapping from a continuous onto a discrete random variable by introducing the second maximum entropy principle, complementary to the Gibbsian one. The mapping corresponds to the self-organization of a community of formal neurons. The derived properties of the interaction between neurons are similar to those in biological neural networks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • `COMPO' conceptual clustering with connectionist competitive learning

    Publication Year: 1989, Page(s):226 - 232
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (472 KB)

    Introduces the idea that conceptual clustering can be performed using connectionist competitive learning. Competitive learning is used to detect clusters of objects and their corresponding (qualitative) descriptions. A genetic algorithm is employed to choose a subset of these descriptions such that the objects matching them form partitions over the population of objects concerned. Hierarchical cla... 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.
  • Building expert systems on neural architecture

    Publication Year: 1989, Page(s):221 - 225
    Cited by:  Papers (3)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (352 KB)

    A novel approach has been developed for building a rule-based system on the neural architecture. Under this approach, the knowledge base and the inference engine are mapped into an entity called conceptualization where a node represents a concept and a link represents a relation between two concepts. Inference in the conceptualization involves propagation and combination of activations as well as ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel architecture for nonlinear adaptive filtering and pattern recognition

    Publication Year: 1989, Page(s):265 - 269
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (292 KB)

    In the late 1950s there were two particular, closely related developments in information processing: the perceptron, based on the work of Rosenblatt (1961) and the adaptive noise canceller of Widrow and Hoff (1960). Subsequently the two ideas progressed in different ways under the patronage of different sections of the scientific community. The present paper centres on an assertion of their origin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrated circuit emulation of ART1 networks

    Publication Year: 1989, Page(s):37 - 41
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (276 KB)

    Adaptive resonance theory (ART) is a neural-network based clustering method developed by G.A. Carpenter and S. Grossberg (1987). Its inspiration is neurobiological and its component parts are intended to model a variety of hierarchical inference levels in the human brain. Neural networks based upon ART are capable of recognizing patterns close to previously stored patterns according to some criter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical self-organising networks

    Publication Year: 1989, Page(s):2 - 6
    Cited by:  Papers (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (344 KB)

    A training scheme for a nonparametric neural network, which leads to the vector quantiser is derived. Then, the robust hidden layer principle is introduced in order to relate the vector quantiser to self-organising neural networks. Finally, it is demonstrated how hierarchical self-organising neural networks may be constructed by further application of the robust hidden layer principle 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.
  • The properties and implementation of the nonlinear vector space connectionist model

    Publication Year: 1989, Page(s):186 - 190
    Cited by:  Papers (7)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (284 KB)

    The nonlinear vector space expansion connectionist model is shown to have a number of advantages over currently applied networks for application to general connectionist problems. Firstly, it converges to its optimal solution far faster, by several orders of magnitude, than previously proposed networks, and this convergence time does not rise as quickly as a function of the size of the pattern vec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • {0,1}n space self-organising feature maps-extensions and hardware implementation

    Publication Year: 1989, Page(s):261 - 264
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (248 KB)

    Discusses a technique for realising self-organising feature maps which exploit the properties of {0,1}n space. Working within the digital domain permits the generation of large fast networks using conventional computing machinery. Though the method exploits some of the methods of conventional N-tuple recognisers, such as WISARD, it differs in that it is an unsupervised learning process ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of plasticity in MOS synapses

    Publication Year: 1989, Page(s):33 - 36
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (216 KB)

    Discusses learning, multiplication and other algorithms for a fully-connected artificial neural network in which synaptic weights between neurons are represented by resistances, the output of a neuron producing an analogue voltage Vi (in the range O to +V0 volts) which is a function of a weighted sum of its inputs. The strength or weight Wij of the connections is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 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 (32 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.
  • 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.
  • A neural network implementation for real-time scene analysis

    Publication Year: 1989, Page(s):71 - 75
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (260 KB)

    A prototype neural network of LSI electronic logic, coupled with a matrix of photodetectors is proposed to implement the preprocessing functions of image capture and region extraction. The structure is described, with its likely implementation strategy, and the full online scene analysis algorithm is explained, with some simulation results made on real and 3D computer generated images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Output functions for probabilistic logic nodes

    Publication Year: 1989, Page(s):310 - 314
    Cited by:  Papers (6)  |  Patents (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (292 KB)

    Probabilistic logic node (PLN) nets consist of RAM-based nodes which can learn any function of their binary inputs; they require only global error signals during training, and they have been shown to solve problems significantly faster that nets learning by error back-propagation. Output functions for PLNs may be probabilistic, linear or sigmoidal in nature. The paper deals with designing an outpu... View full abstract»

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

    Publication Year: 1989, Page(s):211 - 215
    Cited by:  Papers (15)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (284 KB)

    Error back-propagation is a method whereby a neural net can learn to control a plant in an autonomous way, without a specific learning stage. The paper presents an evaluation method for it, based on qualitative knowledge of the plant. The field of application of the method is specified. The proposed method is applied to three different problems. These three simulations investigate the possibility ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Single layer look-up perceptrons

    Publication Year: 1989, Page(s):148 - 152
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (336 KB)

    Concerns a single layer perceptron (SLP) which incorporates n-tuple pattern recognition techniques in an SLP architecture to produce a single layer look-up perceptron (SLLUP) which can learn the same types of nonlinear mappings as a multilayer perceptron but with a fraction of the training and computation. An additional very desirable property of the SLLUP is that it produces a quadratic error sur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unlimited accuracy in layered networks

    Publication Year: 1989, Page(s):181 - 185
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (216 KB)

    It is shown that precision requirements on input units may lead to prohibitive learning times when using standard neural learning algorithms even in very simple cases. Two alternative approaches, which achieve fast learning for any accuracy are proposed. The first is a simple preprocessing of inputs. The second one consists in variants of the perceptron rule and error backpropagation with variable... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision feedback equalization using neural network structures

    Publication Year: 1989, Page(s):125 - 128
    Cited by:  Papers (6)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (184 KB)

    Describes a new approach for a decision feedback equalizer (DFE) using the multi-layer perceptron structure for equalization in digital communications systems. Results indicate that the multi-layer perceptron DFE provides better BER (bit error rate) performance relative to the standard least mean square DFE structure, especially in high noise conditions 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.
  • The implementation of hardware neural net systems

    Publication Year: 1989, Page(s):57 - 61
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (268 KB)

    Describes a multilayer pipelined digital architecture suitable for the implementation of large neural nets (LN) for vision applications. It can also be used to do some pre-filtering, such as pixel averaging, by setting weight values appropriately. A 1024 node processor with a clock rate of 10 MHz can operate on an input vector consisting of 32×32 8 bit pixels in 102 μs. It can therefore p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Weight limiting, weight quantisation and generalisation in multi-layer perceptrons

    Publication Year: 1989, Page(s):297 - 300
    Cited by:  Papers (5)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (236 KB)

    If a multilayer perceptron (MLP) is to be implemented on fixed point hardware then the robustness of the structure to weight quantisation is important. Most work on MLP performance totally neglects this issue and it is only addressed after a network has been trained. It is shown that both generalisation performance and robustness to weight quantisation can be improved by including explicit weight-... View full abstract»

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