Using genetic algorithm with adaptive mutation mechanism for neural networks design and training

Y. R. Tsoy, V. G. Spitsyn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper a developed evolutionary algorithm (NEvA) for simultaneous connections and weights of neural network training is described. A distinctive feature of the algorithm is flexible and effective evolutionary search and a balanced resulting neural network structure due to adaptive mutation operator. In NEvA neural network structure changes, caused by mutation operator, as well as mutation rate are defined independently for each individual. Two different problems are chosen to test the algorithm. The first one is a simple 2-bit parity problem, well known as XOR problem, and the second is a neurocontrol problem of t and 2 poles balancing. A comparison of obtained results with results of other algorithms is presented.

Original languageEnglish
Title of host publicationProceedings - 9th Russian-Korean International Symposium on Science and Technology, KORUS-2005
Pages709-714
Number of pages6
Volume1
DOIs
Publication statusPublished - 2005
Event9th Russian-Korean International Symposium on Science and Technology, KORUS-2005 - Novosibirsk, Russian Federation
Duration: 26 Jun 20052 Jul 2005

Other

Other9th Russian-Korean International Symposium on Science and Technology, KORUS-2005
CountryRussian Federation
CityNovosibirsk
Period26.6.052.7.05

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Using genetic algorithm with adaptive mutation mechanism for neural networks design and training'. Together they form a unique fingerprint.

  • Cite this

    Tsoy, Y. R., & Spitsyn, V. G. (2005). Using genetic algorithm with adaptive mutation mechanism for neural networks design and training. In Proceedings - 9th Russian-Korean International Symposium on Science and Technology, KORUS-2005 (Vol. 1, pp. 709-714). [1507882] https://doi.org/10.1109/KORUS.2005.1507882