论文信息 - Using classifier systems to design neural nets

Using classifier systems to design neural nets

A new neural network training algorithm, based on the use of genetic algorithms and classifier systems, is presented. The algorithm not only calculates the weights of the network links, but also automates the traditionally ad hoc, trial and error method for finding the most appropriate architecture of the neural net.<<ETX>>

Christos Nikolopoulos | C. Nikolopoulos

[1] Peter M. Todd,et al. Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[2] Richard K. Belew,et al. Back Propagation for the Classifier System , 1989, International Conference on Genetic Algorithms.

[3] John H. Holland. Genetic Algorithms and Classifier Systems: Foundations and Future Directions , 1987, ICGA.