Genetic optimisation of control parameters of a neural network

Author

Choi, Belinda ; Bluff, Kevin

Author_Institution

Dept. of Inf. Technol., La Trobe Univ., Bundoora, Vic., Australia

fYear

1995

Firstpage

174

Lastpage

177

Abstract

One of the shortcomings of artificial neural networks (ANNs) is the difficulty in predicting the best control parameters for a certain application. The number of combinations of parameters is very large. This makes it very inefficient and expensive to search manually by trial and error. Genetic algorithms (GAs) are an excellent and effective search technique suitable for this task. This paper describes an investigation into the use of GAs to automate the choice of parameters in both a standard backpropagation (SBP) and a fuzzy backpropagation (FBP) network for different applications

Keywords

backpropagation; fuzzy neural nets; genetic algorithms; neural net architecture; search problems; control parameters; fuzzy backpropagation network; genetic algorithms; genetic optimisation; neural network; neural network architecture; search technique; standard backpropagation network; Artificial neural networks; Frequency; Fuzzy sets; Genetic algorithms; Information technology; Neural networks; Optimal control; Pattern recognition; Space technology; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Neural Networks and Expert Systems, 1995. Proceedings., Second New Zealand International Two-Stream Conference on

Conference_Location

Dunedin

Print_ISBN

0-8186-7174-2

Type

conf

DOI

10.1109/ANNES.1995.499466

Filename

499466