Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/26102

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

Title

Evolving complex neural networks that age

Author(s)

Podlena, John R.;  Hendtlass, Tim

Abstract

The combination of the broad problem searching capabilities of a genetic algorithm with the local maxima location capabilities of a hill climbing algorithm can be a powerful technique for solving classification problems. Producing a number of specialist artificial neural networks, each an expert on one category, can be beneficial when solving problems in which the categories are distinct. This paper describes combining genetic algorithms, hill climbing and sets of specialist artificial neural networks to solve a difficult character recognition problem. It also describes a method by which the effects of a large 'elite' sub-population can be counter-balanced by using an aging coefficient in the fitness calculation.

Publication type

Conference paper

Research centre

Swinburne University of Technology. School of Biophysical Sciences and Electrical Engineering

Source

Proceedings of the IEEE International Conference on Neural Networks (ICNN-95), Perth, Western Australia, Australia, 27 November-01 December 1995, Vol. 2, pp. 590-595

Publication year

1995

Keyword(s)

Ageing coefficient;  Ageing neural networks;  Calculations;  Character recognition;  Complex neural network evolution;  Computational complexity;  Electric network topology;  Elite subpopulation;  Fitness calculation;  Genetic algorithms;  Hill climbing algorithm;  Local maxima location capabilities;  Neural nets;  Neural networks;  Pattern classification;  Problem-searching capabilities;  Problem solving;  Specialist artificial neural networks;  Weight crossover

Publisher

IEEE

ISBN

0780327594

Publisher URL

http://dx.doi.org/10.1109/ICEC.1995.487450

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