Preventing Computational Chaos in Asynchronous Neural Networks

Jacob Barhen, Vladimir Protopopescu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

One of the primary advantages of artificial neural networks is their inherent ability to perform massively parallel, nonlinear signal processing. However, the asynchronous dynamics underlying the evolution of such networks may often lead to the emergence of computational chaos, which impedes the efficient retrieval of information usually stored in the system's attractors. In this paper, we discuss the implications of chaos in concurrent asynchronous computation, and provide a methodology that prevents its emergence. Our results are illustrated on a widely used neural network model.

Original languageEnglish
Title of host publication21st IASTED International Multi-Conference on Applied Informatics
Pages1290-1295
Number of pages6
StatePublished - 2003
Event21st IASTED International Multi-Conference on Applied Informatics - Innsbruck, Austria
Duration: Feb 10 2003Feb 13 2003

Publication series

NameIASTED International Multi-Conference on Applied Informatics
Volume21

Conference

Conference21st IASTED International Multi-Conference on Applied Informatics
Country/TerritoryAustria
CityInnsbruck
Period02/10/0302/13/03

Fingerprint

Dive into the research topics of 'Preventing Computational Chaos in Asynchronous Neural Networks'. Together they form a unique fingerprint.

Cite this