Function approximation on high-dimensional spaces is often thwarted by a lack of sufficient data to adequately "fill" the space, or lack of sufficient computational resources. The technique of local variable selection provides a partial solution to these problems by attempting to approximate functions locally using fewer than the complete set of input dimensions.

We study the evolution of the generalization ability of a simple linear perceptron withN inputs which learns to imitate a "teacher perceptron". The system is trained on p aN binary example inputs and the generalization abilitymeasured by testing for agreement with the teacher on all 2N possible binary input patterns. The dynamics may be solved analytically and exhibits a phase transition from imperfect to perfect generalization at a 1. Except at this point the generalization ability approaches its asymptotic value exponentially, with critical slowing down near the transition; therelaxation time is ex (1 - y'a)-2.

In salamander retina, the response of On-Off ganglion cells to a central flash is reduced by movement in the receptive field surround. Through computer simulation of a 2-D model which takes into account their anatomical and physiological properties, we show that interactions between four neuron types (two bipolar and two amacrine) may be responsible for the generation and lateral conductance of this change sensitive inhibition. The model shows that the four neuron circuit can account for previously observed movement sensitive reductions in ganglion cell sensitivity and allows visualization and prediction of the spatiotemporal pattern of activity in change sensitive retinal cells.

We are concerned with the problem of the number of nodes needed in a feedforward neural network in order to represent a fUllction to within a specified accuracy.

A novel learning control architecture is used for navigation. A sophisticated test-bedis used to simulate a cylindrical robot with a sonar belt in a planar environment. The task is short-range homing in the presence ofobstacles. The robot receives no global information and assumes no comprehensive world model. Instead the robot receives only sensory information which is inherently limited. A connectionist architecture is presented which incorporates a large amount of a priori knowledge in the form of hard-wired networks, architectural constraints, and initial weights. Instead of hard-wiring static potential fields from object models, myarchitecture learnssensor-based potential fields, automatically adjusting them to avoid local minima and to produce efficient homing trajectories. It does this without object models using only sensory information. This research demonstrates the use of a large modular architecture on a difficult task.

In the debate over the power of connectionist models to handle linguistic phenomena, considerableattention has been focused on the learning of simple morphological rules. It is a straightforward matter in a symbolic system to specify how the meanings ofa stem and a bound morpheme combine to yield the meaning of a whole word and how the form of the bound morpheme depends on the shape of the stem. In a distributed connectionist system, however, where there may be no explicit morphemes, words, or rules, things are not so simple. The most important work in this area has been that of Rumelhart and McClelland (1986), together with later extensions by Marchman and Plunkett (1989). The networks involvedwere trained to associate English verb stems with the corresponding past-tense forms, successfully generating both regular and irregular forms and generalizing tonovel inputs. This work established that rule-like linguistic behavior 605 606 Gasser and Lee could be achieved in a system with no explicit rules. However, it did have important limitations, among them the following: 1. The representation of linguistic form was inadequate. This is clear, for example, fromthe fact that distinct lexical items may be associated with identical representations (Pinker & Prince, 1988).

Barto, Sutton and Watkins [2] introduced a grid task as a didactic example oftemporal difference planning and asynchronous dynamical pre gramming. Thispaper considers the effects of changing the coding of the input stimulus, and demonstrates that the self-supervised learning of a particular form of hidden unit representation improves performance.

Bernardo A. Huberman Dynamics of Computation XeroxPARC Palo Alto, CA 94304 Inspired by the information theoretic idea of minimum description length, we add a term to the back propagation cost function that penalizes network complexity. We give the details of the procedure, called weight-elimination, describe its dynamics, and clarify the meaning of the parameters involved. From a Bayesian perspective, the complexity term can be usefully interpreted as an assumption about prior distribution of the weights. We use this procedure to predict the sunspot time series and the notoriously noisy series of currency exchange rates. 1 INTRODUCTION Learning procedures for connectionist networks are essentially statistical devices for performing inductiveinference. There is a tradeoff between two goals: on the one hand, we want such devices to be as general as possible so that they are able to learn a broad range of problems.

Inspired by a visual motion detection model for the ra.bbit retina and by a computational architecture used for early audition in the barn owl, we have designed a chip that employs a correlation model to report the one-dimensional field motion of a scene in real time. Using subthreshold analog VLSI techniques, we have fabricated and successfully tested a 8000 transistor chip using a standard MOSIS process.

The network's performance was analyzed over several simulations with training sets in both English and German.