| 前馈神经网络的混沌BP 混合学习算法 |
| |
| 引用本文： | 李祥飞,邹 恩,邹莉华.前馈神经网络的混沌BP 混合学习算法[J].控制与决策,2004,19(4):462-464. |
| |
| 作者姓名： | 李祥飞 邹 恩 邹莉华 |
| |
| 作者单位： | 株洲工学院,电气工程系,湖南,株洲,412008 |
| |
| 基金项目： | 湖南省自然科学基金资助项目(01JJY3029). |
| |
| 摘 要： | 简要分析由Logistic映射产生的混沌数以及不同混沌序列之间的概率统计特性，为混沌全局性搜索提供了依据．将一种快速BP算法与混沌优化相结合，提出了混沌BP混合算法，由于混沌Logistic映射的遍历性、随机性，使得混合算法收敛速度快，且具有全局性，采用混合算法对XOR问题和非线性函数进行仿真，结果表明该算法明显优于标准BP算法和快速BP算法。
|
| 关 键 词： | 前馈神经网络 混沌优化 BP算法 遍历性 |
| 文章编号： | 1001-0920(2004)04-0462-03 |
| 修稿时间： | 2003年2月23日 |
Chaos BP hybrid learning algorithm for feedforward neural network |
| |
| LI Xiang-fei,ZOU En,ZOU Li-hua.Chaos BP hybrid learning algorithm for feedforward neural network[J].Control and Decision,2004,19(4):462-464. |
| |
| Authors: | LI Xiang-fei ZOU En ZOU Li-hua |
| |
| Abstract: | Probabilistic properties are analyzed for chaotic data and different chaotic sequences generated by Logistic map, which provides theoretical basis for chaos global searching. A chaos-BP hybrid algorithm is proposed by means of combination of a new fast BP algorithm and chaos optimization searching. Due to ergodicity and random of chaotic Logistic map, chaos-BP algorithm converges fast and globally, and has no local minimum. The algorithm is applied to XOR problem and nonlinear function approximation. Simulation results show that the chaos-BP algorithm needs shorter learning time than that of the standard BP and fast BP. |
| |
| Keywords: | feedforward neural network chaos optimization BP algorithm ergodicity |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《控制与决策》浏览原始摘要信息 |
|
点击此处可从《控制与决策》下载全文 |
