Accessibility navigation

Using self-organising feature maps for the control of artificial organisms

Ball, N. R. and Warwick, K. (1993) Using self-organising feature maps for the control of artificial organisms. IEE Proceedings D: Control Theory and Applications, 140 (3). pp. 176-180. ISSN 0143-7054

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

Official URL:


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 the paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results in the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.

Item Type:Article
ID Code:18049
Uncontrolled Keywords:Kohonen feature map, artificial organisms, associative memory, content addressable storage, genetic-based classifier system, goal related feedback, hybrid learning system, local adaptation, long term memory, maze running task, self-organising feature maps

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation