Evolving neural induction regular language using combined evolutionary algorithms

Jinn Moon Yang, Cheng Yan Kao, Jorng Tzong Horng

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

Abstract

This paper proposes a new algorithm called combined evolutionary algorithm (CEA) to train a neural network, and demonstrates its use in inducing thefinite state automata task. This algorithm evolves neural networks by incorporating the ideas of evolutionary programming(EP) and real coded genetic algorithms (RCGA) into evolution strategies (ESs). Simultaneously, we add the local competition into the CEA in order to reduce the complexity and maintain the diversity. This algorithm is able to balance the exploration and exploitation dynamically. We implement CEA and experiment on seven benchmark problems of regular language. The results indicate that the CF-4 is a powerful technique to construct neural networks.

Original languageEnglish
Title of host publicationProceedings ISAI / IFIS 1996 Mexico - USA Collaboration in Intelligent Systems Technologies
EditorsRogelio Soto, Jose M. Sanchez, Francisco J. Cantu-Ortiz, Moraima Campbell
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages162-169
Number of pages8
ISBN (Electronic)9682994373, 9789682994371
StatePublished - 1996
Event1996 Mexico-USA Collaboration in Intelligent Systems Technologies - 1st Joint Conference on Intelligent Systems between the 9th International Symposium on Artificial Intelllgence, ISAI 1996 and the 6th International Conference on Industrial Fuzzy Control and Intelligent Systems, IFIS 1996 - Cancun, Mexico
Duration: 12 Nov 199615 Nov 1996

Publication series

NameProceedings ISAI / IFIS 1996 Mexico - USA Collaboration in Intelligent Systems Technologies

Conference

Conference1996 Mexico-USA Collaboration in Intelligent Systems Technologies - 1st Joint Conference on Intelligent Systems between the 9th International Symposium on Artificial Intelllgence, ISAI 1996 and the 6th International Conference on Industrial Fuzzy Control and Intelligent Systems, IFIS 1996
Country/TerritoryMexico
CityCancun
Period12/11/9615/11/96

Fingerprint

Dive into the research topics of 'Evolving neural induction regular language using combined evolutionary algorithms'. Together they form a unique fingerprint.

Cite this