Parallel genetic algorithms for a neurocontrol problem

Yau Zen Chang*, Justin Chang, Chun Kai Huang

*Corresponding author for this work

Research output: Contribution to conferenceConference Paperpeer-review

8 Scopus citations

Abstract

The major purpose of this work is twofold. One is to understand the capability of genetic algorithms (GAs) in artificial neural networks (ANNs) design problems; the other is to improve the efficiency and reliability of GAs by a coarse-grained parallel processing architecture. A parallel processing architecture is proposed in this paper. Based on the proposed architecture, the ability to allow free exchange of a random number of migration elements between sub-populations of GAs, and to allow system expansion without extra coding, is an innovation. Implementation results of an inverse pendulum controller design problem show that, the migration genetic algorithms based on the proposed scheme offer significant improvements in search repeatability and efficiency over the standard GAs.

Original languageEnglish
Pages4151-4155
Number of pages5
StatePublished - 1999
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 10 07 199916 07 1999

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period10/07/9916/07/99

Fingerprint

Dive into the research topics of 'Parallel genetic algorithms for a neurocontrol problem'. Together they form a unique fingerprint.

Cite this