Skip to main navigation Skip to search Skip to main content

BP neural network optimization based on an improved genetic algorithm

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

An improved Genetic Algorithm based on Evolutionarily Stable Strategy is proposed to optimize the initial weights of BP network in this paper. The improvement of GA lies in the introducing of a new mutation operator under control of a stable factor, which is found to be a very simple and effective searching operator. The experimental results in BP neural network optimization show that this algorithm can effectively avoid BP network converging to local optimum. It is found by comparison that the improved genetic algorithm can almost avoid the trap of local optimum and effectively improve the convergent speed.

Original languageEnglish
Title of host publication2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages64-68
Number of pages5
ISBN (Print)0780375084, 9780780375086
StatePublished - 2002
Externally publishedYes
Event1st International Conference on Machine Learning and Cybernetics, ICMLC 2002 - Beijing, China
Duration: 4 Nov 20025 Nov 2002

Publication series

NameProceedings of 2002 International Conference on Machine Learning and Cybernetics
Volume1

Conference

Conference1st International Conference on Machine Learning and Cybernetics, ICMLC 2002
Country/TerritoryChina
CityBeijing
Period4/11/025/11/02

Keywords

  • Back propagation (BP) algorithm
  • Evolutionarily stable strategy
  • Genetic algorithm
  • Neural network
  • Premature convergence

Fingerprint

Dive into the research topics of 'BP neural network optimization based on an improved genetic algorithm'. Together they form a unique fingerprint.

Cite this