| 一种新的混沌神经网络模型及其动力学分析 |
| |
| 引用本文： | 何振亚,谭营,等.一种新的混沌神经网络模型及其动力学分析[J].东南大学学报(自然科学版),1998,28(6):1-5. |
| |
| 作者姓名： | 何振亚 谭营 |
| |
| 作者单位： | [1]东南大学无线电工程系，南京210096 [2]中国科技大学信息处理研究中心，合肥230000 |
| |
| 基金项目： | 国家攀登计划，国家自然科学基金 |
| |
| 摘 要： | 提出了一种混沌神经网络模型。通过引入暂态混沌和时变增益，该网络比Hopfield型网络具有更加丰富和更为灵活的动力学特性，从而具有更强的搜索全局最优解或近似全局最优解的能力，它可以用于求解各种复杂的优化问题。大量的数字模拟表明网络能较好地解决Hopfield型网络的局部极值问题。
|
| 关 键 词： | 混沌神经网络模型 动力学 神经网络 暂态混沌 时变增益 非线性优化 混沌退火机制 |
A New Model of Chaotic Neural Networks and Its Dynamic Characteristic Analysis |
| |
| He Zhenya,Tan Ying,Wang Baoyun.A New Model of Chaotic Neural Networks and Its Dynamic Characteristic Analysis[J].Journal of Southeast University(Natural Science Edition),1998,28(6):1-5. |
| |
| Authors: | He Zhenya Tan Ying Wang Baoyun |
| |
| Affiliation: | He Zhenya 1 Tan Ying 2 Wang Baoyun 3 |
| |
| Abstract: | By introducing transient chaos and time variant gain, the proposed chaotic neural network has richer and more flexible dynamics than Hopfield like neural networks only with point attractors, so that it can be expected to have higher ability of searching for globally optimal or near optimal solutions. It can be used to solving various complicated optimization problem and associative memories. A lot of simulations show that the network is hardly stuck into local minima. |
| |
| Keywords: | neural network transient chaos time variant gain nonlinear optimization chaotic annealing |
| 本文献已被 CNKI 维普 等数据库收录！ |
