作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (20): 24-25. doi: 10.3969/j.issn.1000-3428.2008.20.009

• 博士论文 • 上一篇    下一篇

遗传前馈神经网络在函数逼近中的应用

陈小平,赵鹤鸣,杨新艳   

  1. (苏州大学电子信息学院,苏州 215021)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-10-20 发布日期:2008-10-20

Application of Genetic Feedforward Neural Network in Function Approximation

CHEN Xiao-ping, ZHAO He-ming, YANG Xin-yan   

  1. (School of Electronics & Information, Soochow University, Suzhou 215021)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-10-20 Published:2008-10-20

摘要: 人工神经网络具有高计算能力、泛化能力和非线性映射等特点,被成功应用于众多领域,但缺乏用于确定其网络拓扑结构、激活函数和训练方法的规则。该文提出利用遗传算法优化前馈神经网络的方法,将网络结构、激活函数和训练方法等编码作为个体,发现最优或次优解,针对特定问题设计较理想的前馈神经网络。介绍遗传算法的具体步骤,对非线性函数逼近进行实验,结果表明优化后前馈神经网络的性能优于由经验确定的前馈神经网络,验证了本文方法的有效性。

关键词: 遗传算法, 人工神经网络, 函数逼近

Abstract: Artificial neural network is successfully applied to solve actual problems in many areas because of its excellent computation ability, universality and nonlinear mapping. There is not a guided formula to specify the network structure, activation function and training method. This paper presents a method to optimize the feedforward neural network by Genetic Algorithm(GA), in which the network structure, activation function and training method are encoded as an individual. With optimum solution founded by GA, the feedforward neural network is satisfied. Steps of GA and an example of nonlinear function approximation are given. The experimental results of nonlinear function approach show that the performance of optimized network is better than that of experiential network and identifies validity of the method.

Key words: genetic algorithm, artificial neural network, function approximation

中图分类号: