Comparison of Genetic Algorithm and Particle Swarm Optimizer When Evolving a Recurrent Neural Network

Matthew Settles¹, Brandon Rodebaugh¹, and Terence Soule¹

Department of Computer Science,
University of Idaho,
Moscow, Idaho U.S.A

Abstract. This paper compares the performance of GAs and PSOs in evolving weights of a recurrent neural network. The algorithms are tested on multiple network topologies. Both algorithms produce successful networks. The GA is more successful evolving larger networks and the PSO is more successful on smaller networks.¹

¹This work supported by NSF EPSCoR EPS-0132626. The experiments were performed on a Beowulf cluster built with funds from NSF grant EPS-80935 and a generous hardware donation from Micron Technologies.

LNCS 2723, p. 148 f.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003