Genetic Programming of Minimal Neural Nets Using Occam's Razor
Byoung‐Tak Zhang, Heinz Mühlenbein · 1993
A genetic programming method is investigated for optimizing both the architecture and the connection weights of multilayer feedforward neural networks. The genotype of eachnetwork is represented as a tree whose depth and width are dynamically adapted to the particular application by specifically defined genetic operators. The weights are trained by a next-ascent hillclimbing search. A new fitness function is proposed that quantifies the principle of Occam's razor. It makes an optimal trade-off between the error fitting ability and the parsimonyofthenetwork.