Existing recurrent net learning algorithms are inadequate. We introduce the conceptual framework of viewing recurrent training as matching vector fields of dynamical systems in phase space. Phasespace reconstruction techniques make the hidden states explicit, reducing temporal learning to a feed-forward problem. In short, we propose viewing iterated prediction [LF88] as the best way of training recurrent networks on deterministic signals. Using this framework, we can train multiple trajectories, insure their stability, and design arbitrary dynamical systems. 1 INTRODUCTION Existing general-purpose recurrent algorithms are capable of rich dynamical behavior. Unfortunately, straightforward applications of these algorithms to training fully-recurrent networks on complex temporal tasks have had much less success than their feedforward counterparts. For example, to train a recurrent network to oscillate like a sine wave (the "hydrogen atom" of recurrent learning), existing techniques such as Real Time Recurrent Learning (RTRL) [WZ89] perform suboptimally. Williams & Zipser trained a two-unit network with RTRL, with one teacher signal. One unit of the resulting network showed a distorted waveform, the other only half the desired amplitude.

More than ten of the most prominent models for the structure and for the activity dependent formation of orientation and ocular dominance columns in the striate cort( x have been evaluated. We implemented those models on parallel machines, we extensively explored parameter space, and we quantitatively compared model predictions with experimental data which were recorded optically from macaque striate cortex. In our contribution we present a summary of our results to date. Briefly, we find that (i) despite apparent differences, many models are based on similar principles and, consequently, make similar predictions, (ii) certain "pattern models" as well as the developmental "correlation-based learning" models disagree with the experimental data, and (iii) of the models we have investigated, "competitive Hebbian" models and the recent model of Swindale provide the best match with experimental data. 1 Models and Data The models for the formation and structure of orientation and ocular dominance columns which we have investigated are summarized in table 1. Models fall into two categories: "Pattern models" whose aim is to achieve a concise description of the observed patterns and "developmental models" which are focussed on the pro- 94

Songbirds learn to imitate a tutor song through auditory and motor learning. We have developed a theoretical framework for song learning that accounts for response properties of neurons that have been observed in many of the nuclei that are involved in song learning. Specifically, we suggest that the anteriorforebrain pathway, which is not needed for song production in the adult but is essential for song acquisition, provides synaptic perturbations and adaptive evaluations for syllable vocalization learning. A computer model based on reinforcement learning was constructed that could replicate a real zebra finch song with 90% accuracy based on a spectrographic measure. The second generation of the birdsong model replicated the tutor song with 96% accuracy.

A fundamental open problem in computer vision-determining pose and correspondence between two sets of points in spaceis solved with a novel, robust and easily implementable algorithm. The technique works on noisy point sets that may be of unequal sizes and may differ by nonrigid transformations. A 2D variation calculates the pose between point sets related by an affine transformation-translation, rotation, scale and shear. A 3D to 3D variation calculates translation and rotation. An objective describing the problem is derived from Mean field theory. The objective is minimized with clocked (EMlike) dynamics. Experiments with both handwritten and synthetic data provide empirical evidence for the method. 1 Introduction

The TNM staging system has been used since the early 1960's to predict breast cancer patient outcome. In an attempt to increase prognostic accuracy, many putative prognostic factors have been identified. Because the TNM stage model can not accommodate these new factors, the proliferation of factors in breast cancer has lead to clinical confusion. What is required is a new computerized prognostic system that can test putative prognostic factors and integrate the predictive factors with the TNM variables in order to increase prognostic accuracy. Using the area under the curve of the receiver operating characteristic, we compare the accuracy of the following predictive models in terms of five year breast cancer-specific survival: pTNM staging system, principal component analysis, classification and regression trees, logistic regression, cascade correlation neural network, conjugate gradient descent neural, probabilistic neural network, and backpropagation neural network. Several statistical models are significantly more ac- 1064 Harry B. Burke, David B. Rosen, Philip H. Goodman

In the last decade the outlines of the neural structures subserving the sense of direction have begun to emerge. Several investigations have shed light on the effects of vestibular input and visual input on the head direction representation. In this paper, a model is formulated of the neural mechanisms underlying the head direction system. The model is built out of simple ingredients, depending on nothing more complicated than connectional specificity, attractor dynamics, Hebbian learning, and sigmoidal nonlinearities, but it behaves in a sophisticated way and is consistent with most of the observed properties ofreal head direction cells. In addition it makes a number of predictions that ought to be testable by reasonably straightforward experiments.

This paper studies the problem of diffusion in Markovian models, such as hidden Markov models (HMMs) and how it makes very difficult the task of learning of long-term dependencies in sequences. Using results from Markov chain theory, we show that the problem of diffusion is reduced if the transition probabilities approach 0 or 1. Under this condition, standard HMMs have very limited modeling capabilities, but input/output HMMs can still perform interesting computations.

We present an analog VLSI chip for parallel analog vector quantization. The MOSIS 2.0 J..Lm double-poly CMOS Tiny chip contains an array of 16 x 16 charge-based distance estimation cells, implementing a mean absolute difference (MAD) metric operating on a 16-input analog vector field and 16 analog template vectors.

Each year people spend a huge amount of time typing. The text people type typically contains a tremendous amount of redundancy due to predictable word usage patterns and the text's structure. This paper describes a neural network system call AutoTypist that monitors a person's typing and predicts what will be entered next. AutoTypist displays the most likely subsequent word to the typist, who can accept it with a single keystroke, instead of typing it in its entirety. The multi-layer perceptron at the heart of Auto'JYpist adapts its predictions of likely subsequent text to the user's word usage pattern, and to the characteristics of the text currently being typed. Increases in typing speed of 2-3% when typing English prose and 10-20% when typing C code have been demonstrated using the system, suggesting a potential time savings of more than 20 hours per user per year. In addition to increasing typing speed, AutoTypist reduces the number of keystrokes a user must type by a similar amount (2-3% for English, 10-20% for computer programs). This keystroke savings has the potential to significantly reduce the frequency and severity of repeated stress injuries caused by typing, which are the most common injury suffered in today's office environment.

Diagnosis of human disease or machine fault is a missing data problem since many variables are initially unknown. Additional information needs to be obtained. The j oint probability distribution of the data can be used to solve this problem. We model this with mixture models whose parameters are estimated by the EM algorithm. This gives the benefit that missing data in the database itself can also be handled correctly. The request for new information to refine the diagnosis is performed using the maximum utility principle. Since the system is based on learning it is domain independent and less labor intensive than expert systems or probabilistic networks. An example using a heart disease database is presented.