ELeaRNT: Evolutionary Learning of Rich Neural Network Topologies
Matteo Matteucci · 2006
AbstractIn this paper we present ELeaRNT, an evolutionary strategy which evolves rich neural network topologies in order to nd an optimal domainspecic nonlinear function approxima-tor with a good generalization performance. The neural networks evolved by the algorithm have a feedforward topology with short-cut connections and arbitrary activation functions at each layer. This kind of topologies has not been thoroughly investigated in lit-erature, but is particularly well suited for nonlinear regression tasks. The experimental results prove that, in such tasks, our algo-rithm can build, in a completely automated way, neural network topologies able to outperform classic neural network models de-signed by hand. Also when applied to classication problems, the performance of the obtained neural networks is fully comparable to that of classic neural networks and in some cases noticeably bet-ter. I.