J4

• 计算机科学 • 上一篇    下一篇

带混合学习算法的多阶段神经模糊系统模型

殷树友1, 黄岚2   

  1. 1. 长春金融高等专科学校 计算机系, 长春 130022; 2. 吉林大学 计算机科学与技术学院, 长春 130012
  • 收稿日期:2007-03-26 修回日期:1900-01-01 出版日期:2008-01-26 发布日期:2008-01-26
  • 通讯作者: 黄岚

Model of Multistage Neural Fuzzy System withHybrid Learning Algorithm

YIN Shuyou1, HUANG Lan2   

  1. 1. Department of Computer, Changchun Finance College, Changchun 130022, China;2. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2007-03-26 Revised:1900-01-01 Online:2008-01-26 Published:2008-01-26
  • Contact: HUANG Lan

摘要: 提出一种基于演绎模糊推理的多阶段神经模糊系统模型, 对于给定的学习样本, 通过结构学习(采用遗传算法)与参数学习(采用误差逆传播神经网络方法)过程, 能够生成适当的演绎模糊规则集, 并通过与单阶段神经模糊系统模型求解Benchmark问题的实验对比, 讨论和分析了该模型的有效性和健壮性.

关键词: 混合学习算法, 多阶段神经模糊系统, 演绎模糊推理

Abstract: A multistage Neural Fuzzy System (NFS) model based on syllogistic fuzzy reasoning is proposed in this paper. From the stipulated inputoutput data pairs, an appropriate syllogistic fuzzy rule set can be generated via structure learning (using Genetic Algorithm) and parameter learning (using Backpropagation Neural Network) proceduresproposed in this paper. In addition, by means of solving Benchmark problem and unmanned vehicl control problem, we discussed and analyzed the performance of the proposed model in terms of effectiveness and robustness as compared with singlestage NFS models.

Key words: hybrid learning algorithm, multistage neural fuzzy system, syllogistic fuzzy reasoning

中图分类号: 

  • TP183