One att·empt at explaining human inferencing is that of spreading activat,ion, particularly in the st.ructured connectionist paradigm. This has resulted in t.he building of systems with semantically nameable nodes which perform inferencing by examining t.he pat,t.erns of activation spread.

I will describe my recent results on the automatic development of fixedwidth recursive distributed representations of variable-sized hierarchal data structures. One implication of this wolk is that certain types of AIstyle data-structures can now be represented in fixed-width analog vectors. Simple inferences can be perfonned using the type of pattern associations that neural networks excel at Another implication arises from noting that these representations become self-similar in the limit Once this door to chaos is opened.

We present a new hypothesis that the cerebellum plays a key role in actively controlling the acquisition of sensory infonnation by the nervous system. In this paper we explore this idea by examining the function of a simple cerebellar-related behavior, the vestibula-ocular reflex or VOR, in which eye movements are generated to minimize image slip on the retina during rapid head movements. Considering this system from the point of view of statistical estimation theory, our results suggest that the transfer function of the VOR, often regarded as a static or slowly modifiable feature of the system, should actually be continuously and rapidly changed during head movements. We further suggest that these changes are under the direct control of the cerebellar cortex and propose experiments to test this hypothesis.

This paper provides a systematic analysis of the recurrent backpropagation (RBP) algorithm, introducing a number of new results. The main limitation of the RBP algorithm is that it assumes the convergence of the network to a stable fixed point in order to backpropagate the error signals. We show by experiment and eigenvalue analysis that this condition can be violated and that chaotic behavior can be avoided. Next we examine the advantages of RBP over the standard backpropagation algorithm. RBP is shown to build stable fixed points corresponding to the input patterns. This makes it an appropriate tool for content addressable memories, one-to-many function learning, and inverse problems.

Learning procedures that measure how random perturbations of unit activities correlate with changes in reinforcement are inefficient but simple to implement in hardware. Procedures like back-propagation (Rumelhart, Hinton and Williams, 1986) which compute how changes in activities affect the output error are much more efficient, but require more complex hardware. GEMINI is a hybrid procedure for multilayer networks, which shares many of the implementation advantages of correlational reinforcement procedures but is more efficient. GEMINI injects noise only at the first hidden layer and measures the resultant effect on the output error. A linear network associated with each hidden layer iteratively inverts the matrix which relates the noise to the error change, thereby obtaining the error-derivatives. No back-propagation is involved, thus allowing unknown non-linearities in the system. Two simulations demonstrate the effectiveness of GEMINI.

We have used analog VLSI technology to model a class of small oscillating biological neural circuits known as central pattern generators (CPG). These circuits generate rhythmic patterns of activity which drive locomotor behaviour in the animal. We have designed, fabricated, and tested a model neuron circuit which relies on many of the same mechanisms as a biological central pattern generator neuron, such as delays and internal feedback. We show that this neuron can be used to build several small circuits based on known biological CPG circuits, and that these circuits produce patterns of output which are very similar to the observed biological patterns. To date, researchers in applied neural networks have tended to focus on mammalian systems as the primary source of potentially useful biological information. However, invertebrate systems may represent a source of ideas in many ways more appropriate, given current levels of engineering sophistication in building neural-like systems, and given the state of biological understanding of mammalian circuits.

To more precisely evaluate the implications of a neuronal model.

The Boltzmann Machine has been introduced as a means to perform global optimization for multimodal objective functions using the principles of simulated annealing. In this paper we consider its utility as a spurious-free content-addressable memory, and provide bounds on its performance in this context. We show how to exploit the machine's ability to escape local minima, in order to use it, at a constant temperature, for unambiguous associative pattern-retrieval in noisy environments. An association rule, which creates a sphere of influence around each stored pattern, is used along with the Machine's dynamics to match the machine's noisy input with one of the pre-stored patterns. Spurious fIxed points, whose regions of attraction are not recognized by the rule, are skipped, due to the Machine's fInite probability to escape from any state. The results apply to the Boltzmann machine and to the asynchronous net of binary threshold elements (Hopfield model'). They provide the network designer with worst-case and best-case bounds for the network's performance, and allow polynomial-time tradeoff studies of design parameters.

K. Y. Goldberg and B. A. Pearlmutter School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 ABSTRACT Computing the inverse dynamics of a robot ann is an active area of research in the control literature. We hope to learn the inverse dynamics by training a neural network on the measured response of a physical ann. The input to the network is a temporal window of measured positions; output is a vector of torques. We train the network on data measured from the first two joints of the CMU Direct-Drive Arm II as it moves through a randomly-generated sample of "pick-and-place" trajectories. We then test generalization with a new trajectory and compare its output with the torque measured at the physical arm.

This tendency to preserve information about the path is not a characteristic of traditional finite-state automata. ENCODING PATH INFORMATION In a different set of experiments, we asked whether the SRN could learn to use the infonnation about the path that is encoded in the hidden units' patterns of activation. In one of these experiments, we tested whether the network could master length constraints. When strings generated from the small finite-state grammar may only have a maximum of 8 letters, the prediction following the presentation of the same letter in position number six or seven may be different. For example, following the sequence'TSSSXXV', 'V' is the seventh letter and only another'V' would be a legal successor.