Using self-organising feature maps for the control of artificial organisms
作者:
N.R.Ball,
K.Warwick,
期刊:
IEE Proceedings D (Control Theory and Applications)
(IET Available online 1993)
卷期:
Volume 140,
issue 3
页码: 176-180
年代: 1993
DOI:10.1049/ip-d.1993.0025
出版商: IEE
数据来源: IET
摘要:
Variations on the standard Kohonen feature map can enable an ordering of the map state space by using only a limited subset of the complete input vector. Also it is possible to employ merely a local adaptation procedure to order the map, rather than having to rely on global variables and objectives. Such variations have been included as part of a hybrid learning system (HLS) which has arisen out of a genetic-based classifier system. In this paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results on the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.
点击下载:
PDF
(636KB)
返 回