| 一种新的混沌神经网络及其应用 |
| |
| 引用本文： | 修春波,刘向东,张宇河,唐运虞.一种新的混沌神经网络及其应用[J].电子学报,2005,33(5):868-870. |
| |
| 作者姓名： | 修春波 刘向东 张宇河 唐运虞 |
| |
| 作者单位： | 1. 天津工业大学自动化系,天津 300160;2. 北京理工大学自动控制系,北京 100081 |
| |
| 基金项目： | 国家自然科学基金，北京理工大学校科研和教改项目 |
| |
| 摘 要： | 提出了一种新的混沌神经元模型,该神经元的激励函数由Gauss和Sigmoid两种函数加和组成的非单调函数构成.通过分岔图及Lyapunov指数的计算,分析了其动力学特性.基于该模型,构造了一种新的具有暂态混沌特性的神经网络,该网络在寻优过程中同时衰减两种退火机制实现混沌退火.通过将特征点匹配问题转化为优化问题,该网络可以实现对目标识别问题的求解.仿真实验验证了该算法的有用性和有效性.
|
| 关 键 词： | 混沌 神经网络 优化 特征点匹配 |
| 文章编号： | 0372-2112(2005)05-0868-03 |
| 收稿时间： | 2004-06-18 |
A Novel Chaotic Neural Network and Its Application |
| |
| XIU Chun-bo,LIU Xiang-dong,ZHANG Yu-he,TANG Yun-yu.A Novel Chaotic Neural Network and Its Application[J].Acta Electronica Sinica,2005,33(5):868-870. |
| |
| Authors: | XIU Chun-bo LIU Xiang-dong ZHANG Yu-he TANG Yun-yu |
| |
| Affiliation: | 1. Department of Automatic Control ,Tianjin Polytechnic University,Tianjin 300160,China;2. Department of Automatic Control,Beijing Institute of Technology,Beijing 100081,China |
| |
| Abstract: | We give a novel chaotic neuron model whose activation function is composed of Gauss and Sigmoid function.It is shown that the model may exhibit a complex dynamic behavior.The most significant bifurcation processes,leading to chaos,are investigated through the computation of the Lyapunov exponents.Based on this neuron model,we propose a novel chaotic neural network,which realizes simulated chaotic anneal by decaying two parameters simultaneously.Transforming the feature points matching problem into the optimization problem,the network can complete the function of the object recognition.The simulation results prove the validity of the algorithm. |
| |
| Keywords: | chaos neural network optimization feature points matching |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
