How good are the reconstructions?

Pentti Kanerva Research Institute for Advanced Computer Science Mail Stop 230-5, NASA Ames Research Center Moffett Field, California 94035 ABSTRACT Contour maps provide a general method for recognizing two-dimensional shapes. All but blank images give rise to such maps, and people are good at recognizing objects and shapes from them. The maps are encoded easily in long feature vectors that are suitable for recognition by an associative memory. These properties of contour maps suggest a role for them in early visual perception. The prevalence of direction-sensitive neurons in the visual cortex of mammals supports this view.

Given a set of input-output training samples, we describe a procedure fordetermining the time sequence of weights for a dynamic neural network to model an arbitrary input-output process. We formulate the input-output mapping problem as an optimal control problem,defining a performance index to be minimized as a function of time-varying weights.

We have used information-theoretic ideas to derive a class of practical andnearly optimal schemes for adapting the size of a neural network. By removing unimportant weights from a network, several improvementscan be expected: better generalization, fewer training examples required, and improved speed of learning and/or classification. The basic idea is to use second-derivative information tomake a tradeoff between network complexity and training set error. Experiments confirm the usefulness of the methods on a real-world application. 1 INTRODUCTION Most successful applications of neural network learning to real-world problems have been achieved using highly structured networks of rather large size [for example (Waibel, 1989; Le Cun et al., 1990a)]. As applications become more complex, the networks will presumably become even larger and more structured.

The hybrid design utilizes digital memories to store the synaptic weights and digital-to-analog converters to perform analog multiplication.

Two approaches were explored which integrate neural net classifiers with Hidden Markov Model (HMM) speech recognizers.

Through a combination linguistic analysis, we are attempting to develop a computational basis for the nature of phonology. We present a connectionist architecture that performs multiple simultaneous insertion, deletion, and mutation operations on sequences of phonemes, and introduce a novel additional primitive, clustering. Clustering provides an interesting alternative to both iterative and relaxation accounts of assimilation processes such as vowel harmony. Our resulting model is efficient because it processes utterances entirely in parallel using only feed-forward circuitry.

Analytic solutions to the information-theoretic evolution equation ofthe connection strength of a three-layer feedforward neural net for visual information processing are presented. The results are (1) the receptive fields of the feature-analysing cells correspond tothe eigenvector of the maximum eigenvalue of the Fredholm integral equation of the first kind derived from the evolution equation of the connection strength; (2) a symmetry-breaking mechanism (parity-violation) has been identified to be responsible forthe changes of the morphology of the receptive field; (3) the conditions for the formation of different morphologies are explicitly identified.

A rigorous analysis on the finite precision computational)Spects of neural network as a pattern classifier via a probabilistic approach is presented.

The performance sensitivity of Albus' CMAC network was studied for the scenario in which faults are introduced into the adjustable weights after training has been accomplished. It was found that fault sensitivity was reduced with increased generalization when "loss of weight" faults were considered, but sensitivity was increased for "saturated weight" faults. 1 INTRODUCTION Fault-tolerance is often cited as an inherent property of neural networks, and is thought by many to be a natural consequence of "massively parallel" computational architectures. Numerous anecdotal reports of fault-tolerance experiments, primarily in pattern classification tasks, abound in the literature. However, there has been surprisingly little rigorous investigation of the fault-tolerance properties of various network architectures in other application areas. In this paper we investigate the fault-tolerance of the CMAC (Cerebellar Model Arithmetic Computer) network [Albus 1975] in a systematic manner. CMAC networks have attracted much recent attention because of their successful application in robotic manipulator control [Ersu 1984, Miller 1986, Lane 1988]. Since fault-tolerance is a key concern in critical control tasks, there is added impetus to study Operational Fault Tolerance of CMAC Networks 341 this aspect of CMAC performance.