西南石油大学学报(自然科学版) ›› 1998, Vol. 20 ›› Issue (1): 96-98.DOI: 10.3863/j.issn.1000-2634.1998.01.025

• 基础研究 • 上一篇    下一篇

基于遗传算法的神经网络结构设计   

陈伟 段永刚 蒋红
  

  1. 西南石油学院计算机系,四川 南充 637001
  • 收稿日期:1996-11-22 修回日期:1900-01-01 出版日期:1998-02-20 发布日期:1998-02-20
  • 通讯作者: 陈伟

Neural Network Structure Design Based on Genetic Algorithms

Chen Wei Duan Yonggang Jang Hong
  

  1. Dept. of Computer Science, SWPI, Sichuan, 637001
  • Received:1996-11-22 Revised:1900-01-01 Online:1998-02-20 Published:1998-02-20
  • Contact: Chen Wei

摘要: 神经网络具有广泛的工程应用前景,但在实际应用中还存在一些困难,如何优化网络结构目前尚无理论指导,应用遗传算法与误差反向传播算法相结合的混合学习过程研究网络结构设计,实例表明通过遗传算法优化网络结构,能够有效地提高网络性能。

关键词: 人工智能, 神经网络, 结构设计

Abstract: Artificial neural network (ANN) can be widely used in engimeering domain, but some difficulties are existed in practical application.So far there is no theory about how to optimize network stucture. In this paper a hybrid learning procedure that combines genetic algorithm (GA) and back-propagation errors algorithms is taken to research network structure designing. Applications show that optimizing the network structure by GA can improve efficiently the performance of ANN.

Key words: Artificial intelligence, Nerve network, Structural design

中图分类号: