french@cogsci.indiana.edu (Bob French) (04/22/91)
Archive-name: ai/neural-nets/french-forgetting/1991-03-29 Archive: cogsci.indiana.edu:/pub/french.forgetting.ps.Z [129.79.238.6] Original-posting-by: Bob French <french@cogsci.indiana.edu> Reposted-by: emv@msen.com (Edward Vielmetti, MSEN) The following brief technical report is available from the Center for Research on Concepts and Cognition at Indiana University: USING SEMI-DISTRIBUTED REPRESENTATIONS TO OVERCOME CATASTROPHIC FORGETTING IN CONNECTIONIST NETWORKS Robert M. French Center for Research on Concepts and Cognition Indiana University 510 North Fess Bloomington, IN 47408 e-mail: french@cogsci.indiana.edu In connectionist networks, newly-learned information rapidly destroys previously-learned information unless the network is continually retrained on the old information. This behavior, known as catastrophic forgetting, is unacceptable both for practical purposes and as a model of mind. This paper advances the claim that catastrophic forgetting is a direct consequence of the overlap distributed representations and can be reduced by reducing this overlap. It is also suggested that there is an inevitable trade-off between generalization and forgetting. A simple algorithm is presented that allows a standard feedforward backpropagation network to develop "semi-distributed representations", thereby significantly reducing the problem of catastrophic forgetting. TO OBTAIN A COPY OF THIS PAPER: unix>ftp cogsci.indiana.edu (or ftp 129.79.238.6) ftp>user: anonymous ftp>passwd: ident ftp>cd pub ftp>binary ftp>get french.forgetting.ps.Z ftp>quit unix>uncompress french.forgetting.ps.Z unix>lpr -P(your laser printer) french.forgetting.ps Hard copies may be requested by sending e-mail to: french@cogsci.indiana.edu or by writing directly to C.R.C.C. at the address indicated above. -- comp.archives file verification cogsci.indiana.edu -rw-r--r-- 1 7962 0 276137 Mar 30 02:05 /pub/french.forgetting.ps.Z found french-forgetting ok cogsci.indiana.edu:/pub/french.forgetting.ps.Z