A memetic accuracy-based neural learning classifier system

@article{OHara2005AMA,
  title={A memetic accuracy-based neural learning classifier system},
  author={Toby O'Hara and Larry Bull},
  journal={2005 IEEE Congress on Evolutionary Computation},
  year={2005},
  volume={3},
  pages={2040-2045 Vol. 3}
}
Learning classifier systems (LCS) traditionally use a binary string rule representation with wildcards added to allow for generalizations over the problem encoding. We have presented a neural network-based representation to aid their use in complex problem domains. Here each rule's condition and action are represented by a small neural network, evolved through the actions of the genetic algorithm. In this paper, we present results from the use of backpropagation to provide local search in… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Classifier Fitness Based on Accuracy

Evolutionary Computation • 1995
View 4 Excerpts
Highly Influenced

A Study of the Lamarckian Evolution of Recurrent Neural Networks IEEE Transactions on Evolutionary Computation , 4 ( l ) : 31 - 42 , 2000

M. W. Mak, W. C. Siu
1999

Get Real! XCS with Continuous-Valued Inputs

Learning Classifier Systems • 1999
View 2 Excerpts

Memetic algorithms : a short introduction

P. Moscato
1999

Similar Papers

Loading similar papers…