Fully recurrent (asymmetrical) networks can be thought of as dynamic systems. The dynamics can be shaped to perform content addressable memories, recognize sequences, or generate trajectories. Unfortunately several problems can arise: First, the convergence in the state space is not guaranteed. Second, the learned fixed points or trajectories are not necessarily stable. Finally, there might exist spurious fixed points and/or spurious "attracting" trajectories that do not correspond to any patterns.

We describe a multi-network, or modular, connectionist architecture that captures that fact that many tasks have structure at a level of granularity intermediate to that assumed by local and global function approximation schemes. The main innovation of the architecture is that it combines associative and competitive learning in order to learn task decompositions. A task decomposition is discovered by forcing the networks comprising the architecture to compete to learn the training patterns. As a result of the competition, different networks learn different training patterns and, thus, learn to partition the input space. The performance of the architecture on a "what" and "where" vision task and on a multi-payload robotics task are presented.

The neocognitron is a neural network for pattern recognition and feature extraction. An analog CCD parallel processing architecture developed at Lincoln Laboratory is particularly well suited to the computational requirements of shared-weight networks such as the neocognitron, and implementation of the neocognitron using the CCD architecture was simulated. A modification to the neocognitron training procedure, which improves network performance under the limited arithmetic precision that would be imposed by the CCD architecture, is presented.

In the debate over the power of connectionist models to handle linguistic phenomena, considerable attention has been focused on the learning of simple morphological rules. It is a straightforward matter in a symbolic system to specify how the meanings of a 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 involved were trained to associate English verb stems with the corresponding past-tense forms, successfully generating both regular and irregular forms and generalizing to novel inputs.

In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.

The recent surge of interest in neural networks and parallel analog computation has motivated the need for compact analog computing blocks. Analog weighting is an important computational function of this class. Analog weighting is the combining of two analog values, one of which is typically varying (the input) and one of which is typically fixed (the weight) or at least varying more slowly. The varying value is "weighted" by the fixed value through the "weighting function", typically multiplication. Analog weighting is most interesting when the overall computational task involves computing the "weighted sum of the inputs."

We present a large vocabulary, continuous speech recognition system based on Linked Predictive Neural Networks (LPNN's). The system uses neural networks as predictors of speech frames, yielding distortion measures which are used by the One Stage DTW algorithm to perform continuous speech recognition. The system, already deployed in a Speech to Speech Translation system, currently achieves 95%, 58%, and 39% word accuracy on tasks with perplexity 5, 111, and 402 respectively, outperforming several simple HMMs that we tested. We also found that the accuracy and speed of the LPNN can be slightly improved by the judicious use of hidden control inputs. We conclude by discussing the strengths and weaknesses of the predictive approach.

We are exploring the significance of biological complexity for neuronal computation. Here we demonstrate that Hebbian synapses in realistically-modeled hippocampal pyramidal cells may give rise to two novel forms of self -organization in response to structured synaptic input. First, on the basis of the electrotonic relationships between synaptic contacts, a cell may become tuned to a small subset of its input space. Second, the same mechanisms may produce clusters of potentiated synapses across the space of the dendrites. The latter type of self-organization may be functionally significant in the presence of nonlinear dendritic conductances.

Empirically, generalization between a training and a test stimulus falls off in close approximation to an exponential decay function of distance between the two stimuli in the "stimulus space" obtained by multidimensional scaling. Mathematically, this result is derivable from the assumption that an individual takes the training stimulus to belong to a "consequential" region that includes that stimulus but is otherwise of unknown location, size, and shape in the stimulus space (Shepard, 1987). As the individual gains additional information about the consequential region-by finding other stimuli to be consequential or nOl-the theory predicts the shape of the generalization function to change toward the function relating actual probability of the consequence to location in the stimulus space. This paper describes a natural connectionist implementation of the theory, and illustrates how implications of the theory for generalization, discrimination, and classification learning can be explored by connectionist simulation. 1 THE THEORY OF GENERALIZATION Because we never confront exactly the same situation twice, anything we have learned in any previous situation can guide us in deciding which action to take in the present situation only to the extent that the similarity between the two situations is sufficient to justify generalization of our previous learning to the present situation. Accordingly, principles of generalization must be foundational for any theory of behavior. In Shepard (1987) nonarbitrary principles of generalization were sought that would be optimum in any world in which an object, however distinct from other objects, is generally a member of some class or natural kind sharing some dispositional property of potential consequence for the individual.

A recurrent back-propagation neural network architecture was then designed to numerically estimate the parameters of an optimal nonlinear control law for landing the aircraft. The performance of the network was then evaluated.