UNSPECIFIED (2002) Using noise to compute error surfaces in connectionist networks: A novel means of reducing catastrophic forgetting. NEURAL COMPUTATION, 14 (7). pp. 1755-1769. ISSN 0899-7667

Full text not available from this repository.

Abstract

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.

Item Type:	Journal Article
Subjects:	Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Journal or Publication Title:	NEURAL COMPUTATION
Publisher:	M I T PRESS
ISSN:	0899-7667
Date:	July 2002
Volume:	14
Number:	7
Number of Pages:	15
Page Range:	pp. 1755-1769
Publication Status:	Published
URI:	http://wrap.warwick.ac.uk/id/eprint/10910

Data sourced from Thomson Reuters' Web of Knowledge

Request changes to a record

Actions (login required)

View Item