Staged training of Neocognitron by evolutionary algorithms

Author

Pan, Zhengjun ; Sabisch, Theo ; Adams, Rod ; Bolouri, Hamid

Author_Institution

Dept. of Comput. Sci., Hertfordshire Univ., Hatfield, UK

Volume

3

fYear

1999

fDate

1999

Abstract

The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. We present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems

Keywords

evolutionary computation; image recognition; learning (artificial intelligence); neural nets; visual perception; Neocognitron; complex neural network; evolutionary algorithms; gradient decent algorithms; image recognition; mammalian visual system; pattern recognition; real world problems; staged training; staged training approach; Artificial neural networks; Computer science; Evolutionary computation; Feature extraction; Image recognition; Laboratories; Neural networks; Pattern recognition; Software engineering; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 1999. CEC 99. Proceedings of the 1999 Congress on

Conference_Location

Washington, DC

Print_ISBN

0-7803-5536-9

Type

conf

DOI

10.1109/CEC.1999.785515

Filename

785515