Associative memory with nonmonotone dynamics

✍ Scribed by Masahiko Morita

• Publisher: Elsevier Science
• Year: 1993
• Tongue: English
• Weight: 729 KB
• Volume: 6
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/s0893-6080(05)80076-0

✦ Synopsis

The dynamics of autocorrelation associative memoo' is c:x'amim, d. and a novel neural dynamics which greatly enhances the ability of associative neural networks is presented. This dynamics is sttch that the otttpttt of some particular neurons is reversed (for a discrete model) or the output./imction is not sigmoid but nonmonotonic (.k~r an analog model). It is also shown by numerical experiments that most ~f the problems ~?[the conventional model are overcome by the improved dynamics. These results arc, important not only fi~r practical purposes but also .~or understanding dynamical properties of associative neural networks.