Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks (1991)
| Venue: | In Proceedings of the 13th Annual Cognitive Science Society Conference |
| Citations: | 30 - 4 self |
BibTeX
@INPROCEEDINGS{French91usingsemi-distributed,
author = {Robert M. French},
title = {Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks},
booktitle = {In Proceedings of the 13th Annual Cognitive Science Society Conference},
year = {1991},
pages = {173--178},
publisher = {Erlbaum}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In connectionist networks, newly-learned information 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 of the system's distributed representations and can be reduced by reducing this overlap. 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. 1 Introduction Catastrophic forgetting is the inability of a neural network to retain old information in the presence of new. New information destroys old unless the old information is continually relearned by the net. McCloskey & Cohen [1990] and Ratcliff [1989] have demonstrated that this is a serious problem with c...
Citations
No citations identified.
