Optimising the topology of complex neural networks

Jiang, Fei; Berry, Hugues; Schoenauer, Marc

Optimising the topology of complex neural networks

Authors

Jiang, Fei

Berry, Hugues

Schoenauer, Marc

Description

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.