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.

This work presents an Attractor Neural Network (ANN) model of Recall and Recognition. It is shown that an ANN model can qualitatively account for a wide range of experimental psychological data pertaining to the these two main aspects of memory access. Certain psychological phenomena are accounted for, including the effects of list-length, wordfrequency, presentation time, context shift, and aging. Thereafter, the probabilities of successful Recall and Recognition are estimated, in order to possibly enable further quantitative examination of the model. 1 Motivation The goal of this paper is to demonstrate that a Hopfield-based [Hop82] ANN model can qualitatively account for a wide range of experimental psychological data pertaining to the two main aspects of memory access, Recall and Recognition. Recall is defined as the ability to retrieve an item from a list of items (words) originally presented during a previous learning phase, given an appropriate cue (cued RecalQ, or spontaneously (free RecalQ. Recognition is defined as the ability to successfully acknowledge that a certain item has or has not appeared in the tutorial list learned before. The main prospects of ANN modeling is that some parameter values, that in former, 'classical' models of memory retrieval (see e.g.

A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained" on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the learning process illustrates a new form of mechanical inference: Induction by phase transition. A small weight adjustment causes a "bifurcation" in the limit behavior of the network.

This paper extends work reported in (Hayashi & Nakai.

The in previ us face recognition systems (Ka R· na e, 19;)y' ......--.-.. scaled to the range [0 -. 8]. Part of the training set and its d' tances between facial elements.

Neural network algorithms have proven useful for recognition of individual, segmented characters. However, their recognition accuracy has been limited by the accuracy of the underlying segmentation algorithm. Conventional, rule-based segmentation algorithms encounter difficulty if the characters are touching, broken, or noisy. The problem in these situations is that often one cannot properly segment a character until it is recognized yet one cannot properly recognize a character until it is segmented. We present here a neural network algorithm that simultaneously segments and recognizes in an integrated system. This algorithm has several novel features: it uses a supervised learning algorithm (backpropagation), but is able to take position-independent information as targets and self-organize the activities of the units in a competitive fashion to infer the positional information. We demonstrate this ability with overlapping hand-printed numerals.

This work addresses three problems with reinforcement learning and adaptive neuro-control: 1. Non-Markovian interfaces between learner and environment.

This is a summary of results with Dyna, a class of architectures for intelligent systems based on approximating dynamic programming methods. Dyna architectures integrate trial-and-error (reinforcement) learning and execution-time planning into a single process operating alternately on the world and on a learned forward model of the world. We describe and show results for two Dyna architectures, Dyna-AHC and Dyna-Q. Using a navigation task, results are shown for a simple Dyna-AHC system which simultaneously learns by trial and error, learns a world model, and plans optimal routes using the evolving world model. We show that Dyna-Q architectures (based on Watkins's Q-Iearning) are easy to adapt for use in changing environments.

A novel learning control architecture is used for navigation. A sophisticated test-bed is used to simulate a cylindrical robot with a sonar belt in a planar environment. The task is short-range homing in the presence of obstacles. The robot receives no global information and assumes no comprehensive world model. Instead the robot receives only sensory information which is inherently limited. A connectionist architecture is presented which incorporates a large amount of a priori knowledge in the form of hard-wired networks, architectural constraints, and initial weights. Instead of hard-wiring static potential fields from object models, myarchitecture learns sensor-based potential fields, automatically adjusting them to avoid local minima and to produce efficient homing trajectories. It does this without object models using only sensory information. This research demonstrates the use of a large modular architecture on a difficult task.

We present a new connectionist planning method [TML90]. By interaction with an unknown environment, a world model is progressively constructed using gradient descent. For deriving optimal actions with respect to future reinforcement, planning is applied in two steps: an experience network proposes a plan which is subsequently optimized by gradient descent with a chain of world models, so that an optimal reinforcement may be obtained when it is actually run. The appropriateness of this method is demonstrated by a robotics application and a pole balancing task.