Multistability in recurrent neural networks
檔案
- 000238324300010.pdf (646.1 KB, Adobe PDF)
日期
2006
類型
系所
期刊名稱
SIAM JOURNAL ON APPLIED MATHEMATICS
卷期與頁次
第 66 卷第 4 期,頁 1301–1320
ISSN
0036-1399
語言
英文
摘要
Stable stationary solutions correspond to memory capacity in the application of associative memory for neural networks. In this presentation, existence of multiple stable stationary solutions for Hopfield-type neural networks with delay and without delay is investigated. Basins of attraction for these stationary solutions are also estimated. Such a scenario of dynamics is established through formulating parameter conditions based on a geometrical setting. The present theory is demonstrated by two numerical simulations on the Hopfield neural networks with delays.