 |
    |
SEPA: Structure Evolution and Parameter Adaptation in Feed-Forward Neural Networks
Paulito P. Palmes, Taichi Hayasaka, and Shiro Usui
Department of Information and Computer Sciences
Toyohashi University of Technology
Toyohashi, 441-8580 Japan
{ppalmes,hayasaka,usui}@bpel.ics.tut.ac.jp
http://www.bpel.ics.tut.ac.jp/
Abstract. In developing algorithms that dynamically changes the structure and weights of ANN (Artificial Neural Networks), there must be a proper balance between network complexity and its generalization capability. SEPA addresses these issues using an encoding scheme where network weights and connections are encoded in matrices of real numbers. Network parameters are locally encoded and locally adapted with fitness evaluation consisting mainly of fast feed-forward operations. Experimental results in some well-known classification problems demonstrate SEPA's high consistency performance in classification, fast convergence, and good optimality of structure.
LNCS 2724, p. 1600 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003