Access to the full text

The 6th International Workshop on Self-Organizing Maps (WSOM), 2007
Bielefeld University, Bielefeld, Germany, September 3 - 6, 2007, Conference Chair: Prof. Helge Ritter, ISBN: 978-3-00-022473-7

In this article we present EANT, "Evolutionary Acquisition of Neural Topologies", a method that creates neural networks (NNs) by evolutionary reinforcement learning. The structure of NNs is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES. EANT can create NNs that are very specialised; they achieve a very good performance while being relatively small. This can be seen in experiments where our method competes with a different one, called NEAT, "NeuroEvolution of Augmenting Topologies", to create networks that control a robot in a visual serving scenario.

DOI: 10.2390/biecoll-wsom2007-118

Siebel, Nils T. ; Krause, Jochen ; Sommer, Gerald  (2007)  Self-Organisation of Neural Topologies by Evolutionary Reinforcement Learning. The 6th International Workshop on Self-Organizing Maps (WSOM), 2007, ISBN: 978-3-00-022473-7
URL: http://biecoll.ub.uni-bielefeld.de/volltexte/2007/168

Copyright note