To illustrate the extent of this additional complexity, Fig. Input 6a shows a schematized circuit for a computational unit of method V

There are three existing connection::;t models in which network states are assigned a computational energy.

To illustrate the extent of this additional complexity, Fig. Input 6ashows a schematized circuit for a computational unit of method V-r

There are three existing connection::;t models in which network states are assigned a computational energy.

Previous work on nets with continuous-valued inputs led to generative procedures to construct convex decision regions with two-layer perceptrons (one hidden layer) and arbitrary decision regions with three-layer perceptrons (two hidden layers). Here we demonstrate that two-layer perceptron classifiers trained with back propagation can form both convex and disjoint decision regions. Such classifiers are robust, train rapidly, and provide good performance with simple decision regions. When complex decision regions are required, however, convergence time can be excessively long and performance is often no better than that of k-nearest neighbor classifiers. Three neural net classifiers are presented that provide more rapid training under such situations.

Proc. AAAI-88, Vol. 2, pp. 607–611

Machine Learning, 1, 11–46.

"Chunks have long been proposed as a basic organizational unit for human memory. More recently chunks have been used to model human learning on simple perceptual-motor skills. In this paper we describe recent progress in extending chunking to be a general learning mechanism by implementing it within a general problem solver. Using the Soar problem-solving architecture, we take significant steps toward a general problem solver that can learn about all aspects of its behavior. We demonstrate chunking in Soar on three tasks: the Eight Puzzle, Tic-Tat-Toe, and a part of the RI computer-configuration task. Not only is there improvement with practice, but chunking also produces significant transfer of learned behavior, and strategy acquisition."Proceedings of the AAAi-84 National Conference. AAAI, University of Texas at Austin, TX, August, 1984.

This chapter focuses on ACT system that embodies the extremely powerful thesis that a single set of learning processes underlies the whole gamut of human learning—from children learning their first language by hearing examples of adult speech to adults learning to program a computer by reading textbook instructions. The computer simulation is called ACT. The ACT theory describes its application to research on abstraction of schemas. In ACT, knowledge is divided into two categories: declarative and procedural. The declarative knowledge is represented in a propositional network similar to semantic network representations.

"The terms adaptation, learning, concept-formation, induction, self-organization, and self-repair have all been used in the context of learning system (LS) research. The research has been conducted within many different scientific communities, however, and these terms have come to have a variety of meanings. It is therefore often difficult to recognize that problems which are described differently may in fact be identical. Learning system models as well are often tuned to the require- ments of a particular discipline and are not suitable for application in related disciplines."In Encyclopedia of Computer Science and Technology, Vol. 11. Dekker