Discovery of backpropagation learning rules using genetic programming
Amr Radi, Riccardo Poli · 2002
The backpropagation learning rule is widespread computational method for training multilayer networks. Unfortunately, backpropagation suffers from several problems. The authors have used genetic programming (GP) to overcome some of these problems and to discover new supervised learning algorithms. A set of such learning algorithms has been compared with the standard backpropagation (SBP) learning algorithm on different problems and has been shown to provide better performances. The study indicates that there exist many supervised learning algorithms better than, but similar to, SEP and that GP can be used to discover them.