Incremental acquisition of neural structures through evolution

Yohannes Kassahun, Jan Hendrik Metzen, Mark Edgington, Frank Kirchner

In: Kay Chen Tan , Dikai Liu , Lingfeng Wang (Hrsg.). Design and Control of Intelligent Robotic Systems. Seiten 187-208 Studies in Computational Intelligence 177 ISBN 3540899324 Springer Verlag 2/2009.


In this contribution we present a novel method, called Evolutionary Acquisition of Neural Topologies (EANT), for evolving the structures and weights of neural networks. The method uses an efficient and compact genetic encoding of a neural network into a linear genome that enables a network’s outputs to be computed without the network being decoded. Furthermore, it uses a nature inspired metalevel evolutionary process where new structures are explored at a larger timescale, and existing structures are exploited at a smaller timescale. Because of this, the method is able to find minimal neural structures for solving a given learning task.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence