The Community for Technology Leaders
Neural Networks, IEEE - INNS - ENNS International Joint Conference on (2009)
Atlanta, Ga, USA
June 14, 2009 to June 19, 2009
ISBN: 978-1-4244-3548-7
pp: 2920-2927
Nils T. Siebel , Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts-University of Kiel, Germany
Jonas Botel , Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts-University of Kiel, Germany
Gerald Sommer , Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts-University of Kiel, Germany
ABSTRACT
In this article we present a new method for the pruning of unnecessary connections from neural networks created by an evolutionary algorithm (neuro-evolution). Pruning not only decreases the complexity of the network but also improves the numerical stability of the parameter optimisation process. We show results from experiments where connection pruning is incorporated into EANT2, an evolutionary reinforcement learning algorithm for both the topology and parameters of neural networks. By analysing data from the evolutionary optimisation process that determines the network's parameters, candidate connections for removal are identified without the need for extensive additional calculations.
INDEX TERMS
CITATION

J. Botel, N. T. Siebel and G. Sommer, "Efficient neural network pruning during neuro-evolution," Neural Networks, IEEE - INNS - ENNS International Joint Conference on(IJCNN), Atlanta, Ga, USA, 2009, pp. 2920-2927.
doi:10.1109/IJCNN.2009.5179035
86 ms
(Ver 3.3 (11022016))