| 陈薇娜,阮炯.一类一般输入输出函数的离散神经元模型的分支[J].数学年刊A辑,2009,30(6):793~802 |
| 一类一般输入输出函数的离散神经元模型的分支 |
| The Bifurcation of a Class of Discrete-Time Neural Networks with a General Activation Function |
| 投稿时间：2008-10-29 |
| DOI： |
| 中文关键词: 离散神经元模型, 倍周期分支, 鞍-结点分支 |
| 英文关键词:Discrete neural networks, Period-doubling bifurcation, Saddle-node bifurcation |
| 基金项目: |
|
| 摘要点击次数: 3287 |
| 全文下载次数: 2616 |
| 中文摘要: |
| 用经典分支理论研究了一类一般输入输出函数的离散神经元模型的分支问题, 得到了该类模型产生倍周期分支和鞍-结点分支的充分条件, 推广了目前特殊的正弦输入输出函数的该类模型的结果. 所得的结果为这一类神经网络的应用提供了重要的理论基础. |
| 英文摘要: |
| By using classical bifurcation theories, the authors investigate a class of discrete-time neural networks with a general activation function, and obtain the sufficient condition of period-doubling bifucation and saddle-node bifucation of this model, which can be regarded as an extension of a sinusoidal activation function. As a result, an important theoretical foundation for the application of this class of neural networks is provided. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|
