计算机应用 ›› 2005, Vol. 25 ›› Issue (07): 1661-1662.DOI: 10.3724/SP.J.0187.2005.01661

• 人工智能 • 上一篇    下一篇

基于免疫遗传算法的多层前向神经网络设计

罗菲,何明一   

  1. 西北工业大学 电子信息学院
  • 收稿日期:2005-01-07 修回日期:2005-03-14 出版日期:2005-07-01 发布日期:2005-07-01
  • 作者简介:罗菲(1979-),男,四川成都人,硕士研究生,主要研究方向:人工免疫系统、人工神经网络、进化算法;何明一(1958-),男,四川盐亭人,博士生导师,主要研究方向:神经网络与智能信息处理、图像工程与可视化、对地观测图像处理、三维信息获取与处理

Multilayer feed-forward neural networks based on immune genetic algorithm

LUO Fei, HE Ming-yi   

  1. Electronic and Information School, Northwestern Polytechnical University
  • Received:2005-01-07 Revised:2005-03-14 Online:2005-07-01 Published:2005-07-01

摘要:

利用一种基于免疫功能的遗传算法,设计多层前向神经网络,用于实现多层前向神经网络结构的确定和权值空间的搜索。仿真实验结果显示该算法具有比遗传算法和动量BP算法更好的全局收敛性和快速学习网络权值的能力。

关键词: 多层前向神经网络, 免疫遗传算法, 抗体, 浓度

Abstract:

An optimizing method based on immune genetic algorithm was presented for designing multilayer feedforward neural network. This algorithm could decide the structure of the multilayer feed-forward neural networks and search the proper weight of this network. The simulation experiments show that this algorithm has the better ability of convergent on whole solution space and the capacity of fast learning than genetic algorithm and momentum BP algorithm.

Key words: multilayer feed-forward neural networks, immune genetic algorithm, antibody, density

中图分类号: