期刊文献+

基于免疫遗传算法的前向神经网络设计 被引量:5

Design of Feedforward Neural Network Based on Immune Genetic Algorithm
下载PDF
导出
摘要 针对传统BP算法训练速度慢、易陷入局部最优等缺点,该文提出了一种采用免疫遗传算法设计前向神经网络的方法。为解决神经网络权值随机初始化带来的问题,介绍了一种基于免疫的多样性模拟退火法(SAND算法)来进行神经网络权值初始化。仿真结果表明,该算法比混合遗传算法有更高的性能。 Aimed at the shortcoming of the traditional BP algorithm, such as the slow training speed, easy to be trapped into the local optimums. etc, a method to design the multi-layer feed-forward neural network based on immune genetic algorithm is proposed. In order to solve the problem of the random initial weights, the strategy of simulated annealing for diversity based on immunity is used to initialize the weight vectors. The simulation results show that the proposed algorithm displays a better performance than the hybrid genetic algorithm does.
作者 洪露 穆志纯
出处 《计算机工程》 EI CAS CSCD 北大核心 2006年第15期179-180,183,共3页 Computer Engineering
关键词 免疫遗传算法 多样性模拟退火法 遗传算法 Immune genetic algorithm Simulated annealing for diversity algorithm Genetic algorithm
  • 相关文献

参考文献6

  • 1Castro L N,Zuben F J.An Immunological Approach to Initialize Feedforward Neural Network Weights[C].Proceedings of ICANNGA,Prague,Czech Republic,2001.
  • 2Martens J P,Weymaere N.An Equalized Error Back-propagation Algorithm for the Online Training of Multiplayer Perceptrons[J].IEEE Trans.on Neural Networks,2002,13(3):532-541.
  • 3Nikolaev N Y,Iba H.Learning Polynomial Feed-forward Neural Networks by Genetic Programming and Back-propagation[J].IEEE Trans.on Neural Networks,2003,14(2):337-350.
  • 4张晓缋,戴冠中,徐乃平.遗传算法种群多样性的分析研究[J].控制理论与应用,1998,15(1):17-23. 被引量:77
  • 5丁永生,任立红.人工免疫系统:理论与应用[J].模式识别与人工智能,2000,13(1):52-59. 被引量:98
  • 6楼顺天 于卫.基于MATLAB的系统分析与设计[M].西安电子科技大学出版社,2000..

二级参考文献7

共引文献185

同被引文献36

引证文献5

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部