Quarterly (winter, spring, summer, fall)
128 pp. per issue
7 x 10, illustrated
ISSN
1064-5462
E-ISSN
1530-9185
2014 Impact factor:
1.39

Artificial Life

Winter 2011, Vol. 17, No. 1, Pages 33-50
(doi: 10.1162/artl_a_00016)
© 2011 Massachusetts Institute of Technology
Noise and the Evolution of Neural Network Modularity
Article PDF (569.31 KB)
Abstract

We study the selective advantage of modularity in artificially evolved networks. Modularity abounds in complex systems in the real world. However, experimental evidence for the selective advantage of network modularity has been elusive unless it has been supported or mandated by the genetic representation. The evolutionary origin of modularity is thus still debated: whether networks are modular because of the process that created them, or the process has evolved to produce modular networks. It is commonly argued that network modularity is beneficial under noisy conditions, but experimental support for this is still very limited. In this article, we evolve nonlinear artificial neural network classifiers for a binary classification task with a modular structure. When noise is added to the edge weights of the networks, modular network topologies evolve, even without representational support.