Neurocomputing: Algorithms, Architectures and Applications(68 NATO ASI Subseries F:)

This volume contains the collected papers of the NATO Conference on Neurocomputing, held in Les Arcs in February 1989. For many of us, this conference was reminiscent of another NATO Conference, in 1985, on Disordered Systems [1], which was the first conference on neural nets to be held in France. To some of the participants that conference opened, in a way, the field of neurocomputing (somewhat exotic at that time!) and also allowed for many future fruitful contacts. Since then, the field of neurocomputing has very much evolved and its audience has increased so widely that meetings in the US have often gathered more than 2000 participants. However, the NATO workshops have a distinct atmosphere of free discussions and time for exchange, and so, in 1988, we decided to go for another session. This was an ~casion for me and some of the early birds of the 1985 conference to realize how much, and how little too, the field had matured.

Table of Contents:
1 Algorithms.- Incorporating knowledge in multi-layer networks: the example of protein secondary structure prediction.- Product units with trainable exponents and multi-layer networks.- Recurrent backpropagation and Hopfield networks.- Optimization of the number of hidden cells in a multilayer perceptron. Validation in the linear case.- Single-layer learning revisited: a stepwise procedure for building and training a neural network.- Synchronous Boltzmann machines and Gibbs fields: learning algorithms.- Fast computation of Kohonen self-organization.- Learning algorithms in neural networks: recent results.- Statistical approach to the Jutten-Herault algorithm.- The N programming language.- Neural networks dynamics.- Dynamical analysis of classifier systems.- Neuro-computing aspects in motor planning and control.- Neural networks and symbolic A.I.- 2 Architectures.- Integrated artificial neural networks: components for higher level architectures with new properties.- Basic VLSI circuits for neural networks.- An analog VLSI architecture for large neural networks.- Analog implementation of a permanent unsupervised learning algorithm.- An analog cell for VLSI implementation of neural networks.- Use of pulse rate and width modulations in a mixed analog/digital cell for artificial neural systems.- Parallel implementation of a multi-layer perceptron.- A monolithic processor array for stochastic relaxation using optical random number generation.- Dedicated neural network: a retina for edge detection.- Neural network applications in the Edinburgh concurrent supercomputer project.- The semi-parallel architectures of neuro computers.- 3 Speech.- Speech coding with multilayer networks.- Statistical inference in multilayer perceptrons and hidden Markov models with applications in continuous speech recognition.- Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition.- Data compression using multilayer perceptrons.- Guided propagation: current state of theory and applications.- Speaker adaptation using multi-layer feed-forward automata and canonical correlation analysis.- Analysis of linear predictive data as speech and of ARM A processes by a class of single-layer connectionist models.- High and low level speech processing by competitive neural networks: from psychology to simulation.- Connected word recognition using neural networks.- 4 Image.- Handwritten digit recognition: applications of neural net chips and automatic learning.- A method to de-alias the scatterometer wind field: a real world application.- Detection of microcalcifications in mammographie images.- What is a feature, that it may define a character, and a character, that it may be defined by a feature?.- A study of image compression with backpropagation.- Distortion invariant image recognition by Madaline and back-propagation learning multi-networks.- An algorithm for optical flow.- 5 Neuro-biology.- Multicellular processing units for neural networks: model of columns in the cerebral cortex.- A potentially powerful connectionist unit: the cortical column.- Complex information processing in real neurons.- Formal approach and neural network simulation of the co-ordination between posture and movement.- Cheapmonkey: comparing an ANN and the primate brain on a simple perceptual task: orientation discrimination.- References.- List of contributors.