A neural network approach to adaptive state-space partitioning

Author

Bing, Zhang ; Grant, Edward

Author_Institution

Turing Inst., Glasgow, UK

fYear

1991

fDate

13-15 Aug 1991

Firstpage

180

Lastpage

183

Abstract

An algorithm that learns to partition the state-space for a machine learned control application is presented, and the idea of competitive learning, a form of unsupervised learning, is introduced. A theoretical framework for a partitioning algorithm that is based on the neural network competitive learning model of T. kohonen´s feature maps (1982, 1984) is developed. This algorithm is aimed at partitioning the BOXES machine learning algorithm. The goal was to enhance the functionality and the learning capability of BOXES by testing partitioning strategies. The modified BOXES algorithm did show an improved learning performance when compared to BOXES but needs to be tested against other known learning algorithms before its capabilities are judged

Keywords

adaptive control; neural nets; state-space methods; BOXES; adaptive state-space partitioning; competitive learning; feature maps; machine learned control application; neural network; unsupervised learning; Adaptive systems; Control engineering; Control systems; Decoding; Humans; Machine learning; Machine learning algorithms; Neural networks; Partitioning algorithms; State-space methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 1991., Proceedings of the 1991 IEEE International Symposium on

Conference_Location

Arlington, VA

ISSN

2158-9860

Print_ISBN

0-7803-0106-4

Type

conf

DOI

10.1109/ISIC.1991.187354

Filename

187354