Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/26086

Download PDF (Published version) (Adobe Acrobat PDF, -1 bytes)

Title

A self organising artificial neural network with problem dependent architecture

Author(s)

Hendtlass, Tim

Abstract

Self organizing maps (SOM) based on a regularly spaced array of nodes are well known. The optimum net site for a particular problem is not, in general, clear a priori. Even when a suitable size has been found, it is hard to get a uniform distribution of information across the net, despite the application of conscience mechanisms. As a result the final net contains passenger nodes which perform little or no useful purpose. This paper describes a three dimensional net developed to overcome the deficiencies of the tradition SOM. It evolves a physical node distribution in response to the data that is presented to it and eliminates passenger nodes. Although described in terms of mapping into three dimensions, the technique is in principle applicable to mapping into any number of dimensions.

Publication type

Conference paper

Research centre

Swinburne University of Technology. School of Biophysical Sciences and Electrical Engineering. Centre for Intelligent Systems

Source

Proceedings IEEE International Conference on Neural Networks (ICNN-95), Perth, Western Australia, Australia, 27 November-01 December 1995, Vol. 2, p. 1111-1115

Publication year

1995

Keyword(s)

Artificial intelligence;  Optimum net site;  Problem dependent structure;  Self organising artificial neural networks;  Self-organising feature maps;  Three dimensional net

Publisher

IEEE

ISBN

0780327683

Publisher URL

http://dx.doi.org/10.1109/ICNN.1995.487578

Copyright

Copyright © 1995 IEEE. Published version of the paper reproduced here in accordance with the copyright policy of the publisher. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Full text

Peer reviewed