DocumentCode
947333
Title
Optimal gradient descent learning for bidirectional associative memories
Author
Perfetti, Renzo
Author_Institution
Istituto di Elettronica, Perugia Univ., Italy
Volume
29
Issue
17
fYear
1993
Firstpage
1556
Lastpage
1557
Abstract
A learning algorithm for bidirectional associative memories (BAMs) is presented, which results in a greatly enhanced storage capacity. The design strategy is formulated as a convex optimisation problem, and then solved by a steepest-descent approach. The proposed method guarantees the storage of all the training pairs as stable states of the BAM. Computer simulation results are presented to demonstrate the performance of the proposed algorithm.<>
Keywords
content-addressable storage; learning (artificial intelligence); memory architecture; neural nets; optimisation; bidirectional associative memories; convex optimisation problem; design strategy; learning algorithm; stable states; steepest-descent approach; storage capacity; training pairs;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:19931037
Filename
234322
Link To Document