Optimising the topology of complex neural networks
Neural and Evolutionary Computing
2007-10-02 v1 Artificial Intelligence
Abstract
In this paper, we study instances of complex neural networks, i.e. neural netwo rks with complex topologies. We use Self-Organizing Map neural networks whose n eighbourhood relationships are defined by a complex network, to classify handwr itten digits. We show that topology has a small impact on performance and robus tness to neuron failures, at least at long learning times. Performance may howe ver be increased (by almost 10%) by artificial evolution of the network topo logy. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.
Cite
@article{arxiv.0710.0213,
title = {Optimising the topology of complex neural networks},
author = {Fei Jiang and Hugues Berry and Marc Schoenauer},
journal= {arXiv preprint arXiv:0710.0213},
year = {2007}
}