DESIGN OF HOPFIELD-TYPE ASSOCIATIVE MEMORY WITH MAXIMAL BASIN OF ATTRACTION
| dc.citation.epage | 2130 | en_US |
| dc.citation.issue | 24 | en_US |
| dc.citation.spage | 2128 | en_US |
| dc.citation.volume | 29 | en_US |
| dc.citation.woscount | 5 | |
| dc.contributor.author | CHANG, JY | en_US |
| dc.contributor.author | WU, CC | en_US |
| dc.contributor.department | 交大名義發表 | zh_TW |
| dc.contributor.department | 電控工程研究所 | zh_TW |
| dc.contributor.department | National Chiao Tung University | en_US |
| dc.contributor.department | Institute of Electrical and Control Engineering | en_US |
| dc.date.accessioned | 2014-12-08T15:04:16Z | |
| dc.date.available | 2014-12-08T15:04:16Z | |
| dc.date.issued | 1993-11-25 | en_US |
| dc.description.abstract | A method is described for enlarging as much as possible the basin of attraction of a Hopfield-type associative memory. The proposed learning rule, a minimum-overlap learning algorithm that includes a threshold parameter, enables a Hopfield-type associative memory to be designed so that the memory will have a maximal basin of attraction. A technique that diminishes the effect of the threshold on the minimum-overlap learning algorithm is devised. Simulation results show that the basin of attraction constructed by the proposed method is indeed larger than that constructed by several well known methods. | en_US |
| dc.identifier.issn | 0013-5194 | en_US |
| dc.identifier.journal | ELECTRONICS LETTERS | en_US |
| dc.identifier.uri | https://ir.lib.nycu.edu.tw/handle/11536/2784 | |
| dc.identifier.wosnumber | WOS:A1993NF18500040 | |
| dc.language.iso | en_US | en_US |
| dc.subject | ASSOCIATIVE MEMORIES | en_US |
| dc.subject | NEURAL NETWORKS | en_US |
| dc.title | DESIGN OF HOPFIELD-TYPE ASSOCIATIVE MEMORY WITH MAXIMAL BASIN OF ATTRACTION | en_US |
| dc.type | Article | en_US |