The major problem that has prevented practical application of analog neuro-LSIs has been poor accuracy due to fluctuating analog device characteristics inherent in each device as a result of manufacturing. This paper proposes a dynamic control architecture that allows analog silicon neural networks to compensate for the fluctuating device characteristics and adapt to a change in input DC level. We have applied this architecture to compensate for input offset voltages of an analog CMOS WTA (Winner-Take-AlI) chip that we have fabricated. Experimental data show the effectiveness of the architecture.

A one-dimensional visual tracking chip has been implemented using neuromorphic,analog VLSI techniques to model selective visual attention in the control of saccadic and smooth pursuit eye movements. Thechip incorporates focal-plane processing to compute image saliency and a winner-take-all circuit to select a feature for tracking. The target position and direction of motion are reported as the target moves across the array. We demonstrate its functionality ina closed-loop system which performs saccadic and smooth pursuit tracking movements using a one-dimensional mechanical eye. 1 Introduction Tracking a moving object on a cluttered background is a difficult task. When more than one target is in the field of view, a decision must be made to determine which target to track and what its movement characteristics are.

Many popular learning rules are formulated in terms of continuous, analoginputs and outputs. Biological systems, however, use action potentials, which are digital-amplitude events that encode analog information in the inter-event interval. Action-potential representations are now being used to advantage in neuromorphic VLSI systems as well. We report on a simple learning rule, based on the Riccati equation described by Kohonen [1], modified for action-potential neuronal outputs. We demonstrate this learning rule in an analog VLSI chip that uses volatile capacitive storage for synaptic weights. We show that our time-dependent learning rule is sufficient to achieve approximate weight normalization and can detect temporal correlations in spike trains.

Two dimensional image motion detection neural networks have been implemented using a general purpose analog neural computer. The neural circuits perform spatiotemporal feature extraction based on the cortical motion detection model of Adelson and Bergen. The neural computer provides the neurons, synapses and synaptic time-constants required to realize the model in VLSI hardware. Results show that visual motion estimation can be implemented with simple sum-andthreshold neuralhardware with temporal computational capabilities. The neural circuits compute general 20 visual motion in real-time.

We present a theoretical framework for population codes which generalizes naturally to the important case where the population provides information about a whole probability distribution over an underlying quantity rather than just a single value. We use the framework to analyze two existing models, and to suggest and evaluate a third model for encoding such probability distributions. 1 Introduction Population codes, where information is represented in the activities of whole populations ofunits, are ubiquitous in the brain. There has been substantial work on how animals should and/or actually do extract information about the underlying encoded quantity.

Optimal Brain Damage (OBD) is a method for reducing the number ofweights in a neural network. OBD estimates the increase in cost function if weights are pruned and is a valid approximation if the learning algorithm has converged into a local minimum. On the other hand it is often desirable to terminate the learning process beforea local minimum is reached (early stopping). In this paper we show that OBD estimates the increase in cost function incorrectly if the network is not in a local minimum. We also show how OBD can be extended such that it can be used in connection withearly stopping.

The softassign quadratic assignment algorithm has recently emerged as an effective strategy for a variety of optimization problems inpattern recognition and combinatorial optimization. While the effectiveness of the algorithm was demonstrated in thousands of simulations, there was no known proof of convergence. Here, we provide a proof of convergence for the most general form of the algorithm.

We address statistical classifier design given a mixed training set consisting ofa small labelled feature set and a (generally larger) set of unlabelled features. This situation arises, e.g., for medical images, where although training features may be plentiful, expensive expertise is required toextract their class labels. We propose a classifier structure and learning algorithm that make effective use of unlabelled data to improve performance.The learning is based on maximization of the total data likelihood, i.e. over both the labelled and unlabelled data subsets. Twodistinct EM learning algorithms are proposed, differing in the EM formalism applied for unlabelled data. The classifier, based on a joint probability model for features and labels, is a "mixture of experts" structure that is equivalent to the radial basis function (RBF) classifier, but unlike RBFs, is amenable to likelihood-based training. The scope of application for the new method is greatly extended by the observation that test data, or any new data to classify, is in fact additional, unlabelled data - thus, a combined learning/classification operation - much akin to what is done in image segmentation - can be invoked whenever there is new data to classify. Experiments with data sets from the UC Irvine database demonstrate that the new learning algorithms and structure achieve substantial performance gains over alternative approaches.

A classifier is called consistent with respect to a given set of classlabeled pointsif it correctly classifies the set. We consider classifiers defined by unions of local separators and propose algorithms for consistent classifier reduction. The expected complexities of the proposed algorithms are derived along with the expected classifier sizes. In particular, the proposed approach yields a consistent reduction ofthe nearest neighbor classifier, which performs "firm" classification, assigning each new object to a class, regardless of the data structure. The proposed reduction method suggests a notion of "soft" classification, allowing for indecision with respect to objects which are insufficiently or ambiguously supported by the data. The performances of the proposed classifiers in predicting stockbehavior are compared to that achieved by the nearest neighbor method. 1 Introduction Certain classification problems, such as recognizing the digits of a hand written zipcode, requirethe assignment of each object to a class. Others, involving relatively small amounts of data and high risk, call for indecision until more data become available. Examples in such areas as medical diagnosis, stock trading and radar detection are well known. The training data for the classifier in both cases will correspond to firmly labeled members of the competing classes.

The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for online back-propagation learning. Within a statistical mechanics framework, numericalstudies show that this model has features which do not exist in previously studied two-layer network models without adjustablebiases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data. 1 INTRODUCTION Recently there has been much interest in the theoretical breakthrough in the understanding ofthe online learning dynamics of multi-layer feedforward perceptrons (MLPs) using a statistical mechanics framework. In the seminal paper (Saad & Solla, 1995), a two-layer network with an arbitrary number of hidden units was studied, allowing insight into the learning behaviour of neural network models whose complexity is of the same order as those used in real world applications. The model studied, a soft committee machine (Biehl & Schwarze, 1995), consists of a single hidden layer with adjustable input-hidden, but fixed hidden-output weights. The average learning dynamics of these networks are studied in the thermodynamic limit of infinite input dimensions in a student-teacher scenario, where a stu.dent network is presented serially with training examples (elS, (IS) labelled by a teacher network of the same architecture but possibly different number of hidden units.