Resolution of associative memory's perplexity using additional information and exceptional knowledge

Atsushi Imura, Hirohide Ushida, Toru Yamaguchi, Tomohiro Takagi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In recent years there has been a renewal of interest for fuzzy associative memories. However it is difficult to apply fuzzy associative memories to complex knowledge processing, because associative memories have poor storage capacity. In this study, we propose a method to resolve associative memories' perplexity which is due to the poor storage capacity. The term `associative memory's perplexity' can be defined by the fact that, after the recalling processing, several undesired nodes may have almost the same activation as the desired ones. Furthermore we apply the proposed method to the construction of a facial expression model and show its effect.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages2117-2120
Number of pages4
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1 Dec 1993
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 25 Oct 199329 Oct 1993

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume3

Conference

ConferenceProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period25/10/9329/10/93

Fingerprint Dive into the research topics of 'Resolution of associative memory's perplexity using additional information and exceptional knowledge'. Together they form a unique fingerprint.

  • Cite this

    Imura, A., Ushida, H., Yamaguchi, T., & Takagi, T. (1993). Resolution of associative memory's perplexity using additional information and exceptional knowledge. In Proceedings of the International Joint Conference on Neural Networks (pp. 2117-2120). (Proceedings of the International Joint Conference on Neural Networks; Vol. 3). Publ by IEEE.