Yet Another Genetic Algorithm for Feed-Forward Neural Networks

Roman Neruda

Abstract

A functional equivalence property of feedforward networks has been proposed to reduce the search space of learning algorithms. We summarize previous results, describing the form of functional equivalence for one-hidden-layer perceptron networks and radial basis function (RBF) networks with Gaussians. The description of equivalence classes is used in a proposition of a genetic learning algorithm which is tested on two simple problems and which outperforms the standard genetic learning procedure.
BibTeX
@inproceedings{neruda1997yet,
  author = {Roman Neruda},
  title = {{Yet Another Genetic Algorithm for Feed-Forward Neural Networks}},
  booktitle = {ICTAI},
  year = {1997},
  doi = {10.1109/tai.1997.632278},
}

Loading related content...

Figure