| 基于多准则的多层模糊神经网络学习算法 |
| |
| 引用本文： | 舒桂清,李力,肖平.基于多准则的多层模糊神经网络学习算法[J].安徽大学学报(自然科学版),2007,31(1):39-42. |
| |
| 作者姓名： | 舒桂清 李力 肖平 |
| |
| 作者单位： | 广东科学技术职业学院,电子工程系,广东,广州,510640;康佳研究院,广东,深圳,518053 |
| |
| 基金项目： | 广东省科技计划基金资助项目（2006813301004）. |
| |
| 摘 要： | 模糊算子函数丢失信息量过大,并且在某些点不存在导数,由此导致在采用传统的误差平方和准则优化网络参数时,有些参数无法得到调整,而且网络容易陷入局部极小,甚至发散.本文提出了一种基于模糊熵准则和误差平方和准则的多准则多层模糊神经网络学习算法,在一定程度上克服了单准则学习算法的局限性.
|
| 关 键 词： | 神经网络 误差平方和 模糊熵 |
| 文章编号： | 1000-2162（2007）01-0039-04 |
| 修稿时间： | 2006-08-29 |
A multi- criteria learning method for multi- layer fuzzy neural networks |
| |
| SHU Gui-qing,LI Li,XIAO Ping.A multi- criteria learning method for multi- layer fuzzy neural networks[J].Journal of Anhui University(Natural Sciences),2007,31(1):39-42. |
| |
| Authors: | SHU Gui-qing LI Li XIAO Ping |
| |
| Institution: | 1. Department of Electronic Engineering, Guangdong Institute of Technology, Guangzhou 510640, China ; 2. Konka Research Ins itute of Konka Group Co. LTD, Shengzhen 518053,China |
| |
| Abstract: | In this paper,a new approach,the multicriteria learning(MCL) algorithm based on a composite criterion including both fuzzy entropy and mean-squared error criterion,is proposed for training multi layer max-min neural networks.The new algorithm overcomes the limitations in mono-criterion learning,that is,the mean-squared error criterion will easily converging to a local minimum value and slow converging speed.Compared with the traditional fuzzy back-propagation(FBP) algorithm,it is found that the proposed MCL algorithm provides a faster learning speed and higher stability. |
| |
| Keywords: | fuzzy neural networks fuzzy entropy mean-squared error |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
