KMS Of Academy of mathematics and systems sciences, CAS
| Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-output function | |
| Wang, JL; Chen, LN; Jing, ZJ | |
| 2001-02-01 | |
| 发表期刊 | SCIENCE IN CHINA SERIES A-MATHEMATICS PHYSICS ASTRONOMY
![]() |
| ISSN | 1006-9283 |
| 卷号 | 44期号:2页码:193-200 |
| 摘要 | We theoretically investigate the asymptotical stability, local bifurcations and chaos of discrete-time recurrent neural networks with the form of [GRAPHICS] where the input-output function is defined as a generalized sigmoid function, such as v(j) = tanh(mu (j)mu (j)), v(i) = 2/pi arctan(pi /2 mu (i)u(i)) and v(i) = 1/1 + Theta (-u)(/E)(i), etc. Numerical simulations are also provided to demonstrate the theoretical results. |
| 关键词 | chaos asymptotical stability bifurcation neural network snap-back repeller |
| 语种 | 英语 |
| WOS研究方向 | Mathematics |
| WOS类目 | Mathematics, Applied ; Mathematics |
| WOS记录号 | WOS:000167195800006 |
| 出版者 | SCIENCE PRESS |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://ir.amss.ac.cn/handle/2S8OKBNM/16034 |
| 专题 | 中国科学院数学与系统科学研究院 |
| 通讯作者 | Wang, JL |
| 作者单位 | 1.Chinese Acad Sci, Math Inst, Beijing 100080, Peoples R China 2.Osaka Sangyo Univ, Osaka 5748530, Japan 3.Hunan Normal Univ, Dept Math, Changsha 410081, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, JL,Chen, LN,Jing, ZJ. Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-output function[J]. SCIENCE IN CHINA SERIES A-MATHEMATICS PHYSICS ASTRONOMY,2001,44(2):193-200. |
| APA | Wang, JL,Chen, LN,&Jing, ZJ.(2001).Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-output function.SCIENCE IN CHINA SERIES A-MATHEMATICS PHYSICS ASTRONOMY,44(2),193-200. |
| MLA | Wang, JL,et al."Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-output function".SCIENCE IN CHINA SERIES A-MATHEMATICS PHYSICS ASTRONOMY 44.2(2001):193-200. |
| 条目包含的文件 | 条目无相关文件。 | |||||
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论