Associative memory based real-valued pattern recall

Humberto Sossa, Ricardo Barrón, José L. Oropeza, Hector Cortés

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We describe a set of associative memories useful to recall real-valued patterns in the presence of mixed noise. Numerical and real examples are provided to show the efficiency of the proposal. Conditions under which the proposed memories are able to recall patterns either from the fundamental set of patterns and from distorted versions of them are also given.

Original languageEnglish
Title of host publicationProceedings of the Fifth Mexican International Conference in Computer Science, ENC 2004
EditorsR. Baeza-Yates, J.L. Marroquin, E. Chavez
Pages206-212
Number of pages7
DOIs
StatePublished - 2004
EventProceedings of the Fifth Mexican International Conference in Computer Science, ENC 2004 - Colima, Mexico
Duration: 20 Sep 200424 Sep 2004

Publication series

NameProceedings of the Fifth Mexican International Conference in Computer Science, ENC 2004

Conference

ConferenceProceedings of the Fifth Mexican International Conference in Computer Science, ENC 2004
Country/TerritoryMexico
CityColima
Period20/09/0424/09/04

Fingerprint

Dive into the research topics of 'Associative memory based real-valued pattern recall'. Together they form a unique fingerprint.

Cite this