Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

March 2006, Vol. 18, No. 3, Pages 729-747
(doi: 10.1162/neco.2006.18.3.729)
© 2006 Massachusetts Institute of Technology
Connection and Coordination: The Interplay Between Architecture and Dynamics in Evolved Model Pattern Generators
Article PDF (855.69 KB)
Abstract

We undertake a systematic study of the role of neural architecture in shaping the dynamics of evolved model pattern generators for a walking task. First, we consider the minimum number of connections necessary to achieve high performance on this task. Next, we identify architectural motifs associated with high fitness. We then examine how high-fitness architectures differ in their ability to evolve. Finally, we demonstrate the existence of distinct parameter subgroups in some architectures and show that these subgroups are characterized by differences in neuron excitabilities and connection signs.