Evolutionary artificial neural networks
- 22 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 313-317
- https://doi.org/10.1109/ccece.1997.614852
Abstract
We present experiments which show that a genetic algorithm(GA) can effectively search for a set of local feature detectors,which can be used by higher neural network layers toperform an image classification task. Three different methodsof encoding hidden unit weights into the GA are presented,including one which coevolves all the feature detectors ina single chromosome, and two which promote the cooperationof feature detectors by encoding them in their own chromosome.The fitness...Keywords
This publication has 4 references indexed in Scilit:
- Combinations of genetic algorithms and neural networks: a survey of the state of the artPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Use of genetic algorithms with backpropagation in training of feedforward neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic design of cellular neural networks by means of genetic algorithms: finding a feature detectorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Efficient reinforcement learning through symbiotic evolutionMachine Learning, 1996