A novel encoding strategy for associative memory
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractA novel encoding strategy for neural associative memory is presented in this paper. Unlike the conventional pointwise outer-product rule used in the Hopfield-type associative memories, the proposed encoding method computes the connection weight between two neurons by summing up not only the products of the corresponding two bits of all fundamental memories but also the products of their neighboring bits. Theoretical results concerning stability and attractivity are given. It is found both theoretically and experimentally that the proposed encoding scheme is an ideal approach for making the fundamental memories fLxed points and maximizing the storage capacity which can be many times of the current limits.
All Author(s) ListJi H.-B., Leung K.S., Leung Y.
Name of Conference1996 International Conference on Artificial Neural Networks, ICANN 1996
Start Date of Conference16/07/1996
End Date of Conference19/07/1996
Place of ConferenceBochum
Country/Region of ConferenceGermany
Volume Number1112 LNCS
PublisherSpringer Verlag
Place of PublicationGermany
Pages21 - 27
LanguagesEnglish-United Kingdom

Last updated on 2021-16-01 at 00:52