HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by French, R. M. Articles by Chater, N. Search for Related Content PubMed PubMed Citation Articles by French, R. M. Articles by Chater, N.

Using Noise to Compute Error Surfaces in Connectionist Networks: A Novel Means of Reducing Catastrophic Forgetting

rfrench{at}ulg.ac.be, Quantitative Psychology and Cognitive Science, Psychology Department, University of Liège, 4000 Liège, Belgium

Nick Chater

nick.chater{at}warwick.ac.uk, Institute for Applied Cognitive Science, Department of Psychology, University of Warwick Coventry, CV4 7AL, U.K.

In error-driven distributed feedforward networks, new information typically interferes, sometimes severely, with previously learned information. We show how noise can be used to approximate the error surface of previously learned information. By combining this approximated error surface with the error surface associated with the new information to be learned, the network's retention of previously learned items can be improved and catastrophic interference significantly reduced. Further, we show that the noise-generated error surface is produced using only first-derivative information and without recourse to any explicit error information.