However, a large class of continuous control problems require maintaining the system at a desired operating point, or setpoint, at a given time. We refer to this problem as the basic setpoint control problem [Guha 90], and have shown that reinforcement learning can be used, not surprisingly, quite well for such control tasks. A more general version of the same problem requires steering the system from some 479 480 Guha initial or starting state to a desired state or setpoint at specific times without knowledge of the dynamics of the system. We therefore wish to examine how control scheduling tasks, where the system must be steered through a sequence of setpoints at specific times.

Recent progress in network design demonstrates that nonlinear feedforward neural networkscan perform impressive pattern classification for a variety of real-world applications (e.g., Le Cun et al., 1990; Waibel et al., 1989). Various simulations and relationships between the neural network and machine learning theoretical literatures alsosuggest that too large a number of free parameters ("weight overfitting") could substantially reduce generalization performance.

This work extends computational learning theory to situations in which concepts vary over time, e.g., system identification of a time-varying plant. We have extended formal definitions of concepts and learning to provide a framework in which an algorithm can track a concept as it evolves over time. Given this framework and focusing on memory-based algorithms, we have derived some PACstyle sample complexity results that determine, for example, when tracking is feasible. We have also used a similar framework and focused on incremental tracking algorithms for which we have derived some bounds on the mistake or error rates for some specific concept classes. 1 INTRODUCTION The goal of our ongoing research is to extend computational learning theory to include concepts that can change or evolve over time. For example, face recognition is complicated bythe fact that a persons face changes slowly with age and more quickly with changes in make up, hairstyle, or facial hair.

In 4 of these methods the gradient is divided component-wise by a decaying average of either the second derivatives or their absolute values.

We have been studying the performance of a bottlenosed dolphin on a delayed matching-to-sample task to gain insight into the processes and mechanisms that the animal uses during echolocation. The dolphin recognizes targets by emitting natural sonar signals and listening to the echoes that return. This paper describes a novel neural network architecture, called an integrator gateway network, that we have developed toaccount for this performance. The integrator gateway network combines information from multiple echoes to classify targets with about 90% accuracy. In contrast, a standard backpropagation network performed with only about 63% accuracy.

ABSTRACT A large number of VLSI implementationsof neural networkmodels have been reported. The diversityof these implementations is noteworthy. This paper attempts to put a group of representative VLSI implementations in perspective by comparing and contrasting them. IMPLEMENTATION Changing the way information is represented can be beneficial. For examplea change of representation can make information more compact for storage and transmission.

Atkeson Brain and Cognitive Sciences Department and the Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA 02139 Abstract We examine the ability of radial basis functions (RBFs) to generalize. We compare the performance of several types of RBFs. We use the inverse dynamics ofan idealized two-joint arm as a test case. We find that without a proper choice of a norm for the inputs, RBFs have poor generalization properties. A simple global scaling of the input variables greatly improves performance.

Scott E. Fahlman School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Abstract Recurrent Cascade-Correlation CRCC) is a recurrent version of the Cascade Correlation learning architecture of FahIman and Lebiere [Fahlman, 1990]. RCC can learn from examples to map a sequence of inputs into a desired sequence of outputs. New hidden units with recurrent connections are added to the network as needed during training. In effect, the network builds up a finite-state machine tailored specifically for the current problem. RCC retains the advantages of Cascade-Correlation: fast learning, good generalization, automatic construction of a near-minimal multi-layered network, and incremental training. Initially the network contains only inputs, output units, and the connections between them. This single layer of connections is trained (using the Quickprop algorithm [Fahlman, 1988]) to minimize the error.

Box 808 (L-426), Livermore, Ca. 94550 A simple architecture and algorithm for analytically guaranteed associative memorystorage of analog patterns, continuous sequences, and chaotic attractors in the same network is described. A matrix inversion determines network weights, given prototype patterns to be stored.

The development of projections from the retinas to the cortex is mathematically analyzed according to the previously proposed thermodynamic formulation of the self-organization of neural networks. Three types of submodality included in the visual afferent pathways are assumed in two models: model (A), in which the ocularity and retinotopy are considered separately, and model (B), in which on-center/off-center pathways are considered in addition to ocularity and retinotopy. Model (A) shows striped ocular dominance spatial patterns and, in ocular dominance histograms, reveals a dip in the binocular bin. Model (B) displays spatially modulated irregular patterns and shows single-peak behavior in the histograms. When we compare the simulated results with the observed results, it is evident that the ocular dominance spatial patterns and histograms for models (A) and (B) agree very closely with those seen in monkeys and cats.