標題: | Multistability in recurrent neural networks |
作者: | Cheng, CY Lin, KH Shih, CW 應用數學系 Department of Applied Mathematics |
關鍵字: | neural network;multistability;delay equations |
公開日期: | 2006 |
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. |
URI: | http://hdl.handle.net/11536/12771 http://dx.doi.org/10.1137/050632440 |
ISSN: | 0036-1399 |
DOI: | 10.1137/050632440 |
期刊: | SIAM JOURNAL ON APPLIED MATHEMATICS |
Volume: | 66 |
Issue: | 4 |
起始頁: | 1301 |
結束頁: | 1320 |
顯示於類別: | 期刊論文 |