Stochastic automata and learning systems

Thathachar, MAL (1990) Stochastic automata and learning systems. In: Sadhana, 15 (4-5). pp. 263-281.

PDF 348.pdf Download (1MB)

Abstract

We consider stochastic automata models of learning systems in this article. Such learning automata select the best action out of a finite number of actions by repeated interaction with the unknown random environment in which they operate. The selection of an action at each instant is done on the basis of a probability distribution which is updated according to a learning algorithm. Convergence theorems for the learning algorithms are available. Moreover the automata can be arranged in the form of teams and hierarchies to handle complex learning problems such as pattern recognition. These interconnections of learning automata could be regarded as artificial neural networks.

Item Type:	Journal Article
Publication:	Sadhana
Publisher:	Indian Academy of Sciences
Additional Information:	Copyright of this article belongs to Indian Academy of Sciences
Keywords:	Stochastic automata; learning systems; artificial neural networks.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	07 Mar 2008
Last Modified:	19 Sep 2010 04:43
URI:	http://eprints.iisc.ac.in/id/eprint/13308

Actions (login required)

View Item