The vestibulo-ocular reflex (VOR) is the primary mechanism that controls the compensatory eye movements that stabilize retinal images during rapid head motion. The primary pathways of this system are feed-forward, with inputs from the semicircular canals and outputs to the oculomotor system. Since visual feedback is not used directly in the VOR computation, the system must exploit motor learning to perform correctly. Lisberger(1988) has proposed a model for adapting the VOR gain using image-slip information from the retina. We have designed and tested analog very largescale integrated (VLSI) circuitry that implements a simplified version of Lisberger's adaptive VOR model.

We introduce a cost function for learning in feed-forward neural networks which is an explicit function of the internal representation in addition to the weights. The learning problem can then be formulated as two simple perceptrons and a search for internal representations. Back-propagation is recovered as a limit. The frequency of successful solutions is better for this algorithm than for back-propagation when weights and hidden units are updated on the same timescale i.e. once every learning step. 1 INTRODUCTION In their review of back-propagation in layered networks, Rumelhart et al. (1986) describe the learning process in terms of finding good "internal representations" of the input patterns on the hidden units. However, the search for these representations is an indirect one, since the variables which are adjusted in its course are the connection weights, not the activations of the hidden units themselves when specific input patterns are fed into the input layer. Rather, the internal representations are represented implicitly in the connection weight values. More recently, Grossman et al. (1988 and 1989)1 suggested a way in which the search for internal representations could be made much more explicit.

A methodology for faster supervised learning in dynamical nonlinear neural networks is presented. It exploits the concept of adjoint operntors to enable computation of changes in the network's response due to perturbations in all system parameters, using the solution of a single set of appropriately constructed linear equations. The lower bound on speedup per learning iteration over conventional methods for calculating the neuromorphic energy gradient is O(N2), where N is the number of neurons in the network. 1 INTRODUCTION The biggest promise of artifcial neural networks as computational tools lies in the hope that they will enable fast processing and synthesis of complex information patterns. In particular, considerable efforts have recently been devoted to the formulation of efficent methodologies for learning (e.g., Rumelhart et al., 1986; Pineda, 1988; Pearlmutter, 1989; Williams and Zipser, 1989; Barhen, Gulati and Zak, 1989). The development of learning algorithms is generally based upon the minimization of a neuromorphic energy function. The fundamental requirement of such an approach is the computation of the gradient of this objective function with respect to the various parameters of the neural architecture, e.g., synaptic weights, neural Adjoint Operator Algorithms 499

The midbrain of the barn owl contains a map-like representation of sound source direction which is used to precisely orient the head toward targets of interest. Elevation is computed from the interaural difference in sound level. We present models and computer simulations of two stages of level difference processing which qualitatively agree with known anatomy and physiology, and make several striking predictions. 1 INTRODUCTION

In 1877 the Italian astronomer number of inferences about what has Program co-chairpersons are Dr. Robin Giovanni Schiaparaelli announced not changed as the result of performing Cohen of the University of Waterloo, the existence of canali on Mars: a network some action A while allowing the Bob Kass of the EDS Center for of straight and curved lines running small number of inferences about Machine Intelligence, and Cecile Paris across the planet. Canali, meaning what has changed as a result of A. of the Information Sciences Institute.

The 1988 Workshop on Principles of Hybrid Reasoning, a one-day AAAI-sponsored workshop, was held in St. Paul, Minnesota on August 21, 1988, in conjunction with the National Conference on Artificial Intelligence. This article reports on the workshop and presents some of our afterthoughts based upon prolonged discussion of the issues that arose during the workshop.

Based on the experience in manufacturing production scheduling problems which the AI community has amassed over the last ten years, a workshop was held to provide a forum for discussion of the issues encountered in the design of AI-based scheduling systems. Several topics were addressed including : the relative virtues of expert system, deep method, and interactive approaches, the balance between predictive and reactive components in a scheduling system, the maintenance of convenient scheduling descriptions, the application of the ideas of chaos theory to scheduling, the state of the art in schedulers which learn, and the practicality and desirability of a set of benchmark scheduling problems. This article expands on these issues, abstracts the papers which were presented, and summarizes the lengthy discussions that took place.

The growth in the amount of available databases far outstrips the growth of corresponding knowledge. This creates both a need and an opportunity for extracting knowledge from databases. Many recent results have been reported on extracting different kinds of knowledge from databases, including diagnostic rules, drug side effects, classes of stars, rules for expert systems, and rules for semantic query optimization.

The Full-Sized Knowledge-Based Systems Research Workshop was held May 7-8, 1990 in Washington, D.C., as part of the AI Systems in Government Conference sponsored by IEEE Computer Society, Mitre Corporation and George Washington University in cooperation with AAAI. The goal of the workshop was to convene an international group of researchers and practitioners to share insights into the problems of building and deploying Full-Sized Knowledge Based Systems (FSKBSs).

With increases in the complexity of information that must be communicated either by or to computer comes a corresponding need to find ways to communicate that information simply and effectively. It makes little sense to force the burden of communication on a single medium, restricted to just one of spoken or written text, gestures, diagrams, or graphical animation, when in many situations information is only communicated effectively through combinations of media.