Learning Algorithms Theory and Applications: Theory and Applications

by S. Lakshmivarahan

Overview

Learning constitutes one of the most important phase of the whole psychological processes and it is essential in many ways for the occurrence of necessary changes in the behavior of adjusting organisms. In a broad sense influence of prior behavior and its consequence upon subsequent behavior is usually accepted as a definition of learning. Till recently learning was regarded as the prerogative of living beings. But in the past few decades there have been attempts to construct learning machines or systems with considerable success. This book deals with a powerful class of learning algorithms that have been developed over the past two decades in the context of learning systems modelled by finite state probabilistic automaton. These algorithms are very simple iterative schemes. Mathematically these algorithms define two distinct classes of Markov processes with unit simplex (of suitable dimension) as its state space. The basic problem of learning is viewed as one of finding conditions on the algorithm such that the associated Markov process has prespecified asymptotic behavior. As a prerequisite a first course in analysis and shastic processes would be an adequate preparation to pursue the development in various chapters.

Product Details

ISBN-13:	9780387906409
Publisher:	Springer New York
Publication date:	11/02/1981
Edition description:	Softcover reprint of the original 1st ed. 1981
Pages:	280
Product dimensions:	6.10(w) x 9.25(h) x 0.01(d)

Table of Contents

1.Theory.- 1. Introduction.- 2. Ergodic Learning Algorithms.- 3. Absolutely Expedient Learning Algorithms.- 4. Time Varying Leading Algorithms.- II. Applications.- 5. Two-Person Zero-Sum Sequential, Shastic Games with Imperfect and Incomplete Information-Game Matrix with Saddle-Point in Pure Strategies.- 6. Two-Person Zero-Sum Sequential, Shastic Games with Imperfect and Incomplete Information — General Case.- 7. Two-Person Decentralised Team Problem with Incomplete Information.- 8. Control of a Markov Chain with Unknown Dynamics and Cost-Structure.- Epilogue.- Epilogue.- References.