A genetic algorithm with adaptive mutations and family competition for training neural networks.

Jinn-Moon Yang*, J. T. Horng, C. Y. Kao

*Corresponding author for this work

Research output: Contribution to journalArticle

10 Scopus citations

Abstract

In this paper, we present a new evolutionary technique to train three general neural networks. Based on family competition principles and adaptive rules, the proposed approach integrates decreasing-based mutations and self-adaptive mutations to collaborate with each other. Different mutations act as global and local strategies respectively to balance the trade-off between solution quality and convergence speed. Our algorithm is then applied to three different task domains: Boolean functions, regular language recognition, and artificial ant problems. Experimental results indicate that the proposed algorithm is very competitive with comparable evolutionary algorithms. We also discuss the search power of our proposed approach.

Original languageEnglish
Pages (from-to)333-352
Number of pages20
JournalInternational journal of neural systems
Volume10
Issue number5
DOIs
StatePublished - 1 Jan 2000

Fingerprint Dive into the research topics of 'A genetic algorithm with adaptive mutations and family competition for training neural networks.'. Together they form a unique fingerprint.

  • Cite this