TY - GEN
T1 - Evolving multilayer neural networks using permutation free encoding technique
AU - Das, Anupam
AU - Abdullah, Saeed Muhammad
PY - 2009
Y1 - 2009
N2 - In this paper we present an evolutionary system using genetic algorithm (GA) for evolving artificial neural networks (ANNs). Existing genetic algorithms for evolving ANNs suffer from the permutation problem as a result of recombination. Here we propose a novel encoding scheme for representing ANNs which avoids the permutation problem while efficiently evolving multilayer ANN architectures. The evolutionary system has been implemented and tested on a number of benchmark problems in machine learning and neural networks. Experimental results suggest that the system shows superiority in performance, in most of the cases.
AB - In this paper we present an evolutionary system using genetic algorithm (GA) for evolving artificial neural networks (ANNs). Existing genetic algorithms for evolving ANNs suffer from the permutation problem as a result of recombination. Here we propose a novel encoding scheme for representing ANNs which avoids the permutation problem while efficiently evolving multilayer ANN architectures. The evolutionary system has been implemented and tested on a number of benchmark problems in machine learning and neural networks. Experimental results suggest that the system shows superiority in performance, in most of the cases.
UR - http://www.scopus.com/inward/record.url?scp=84866076523&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866076523&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84866076523
SN - 9781601321091
T3 - Proceedings of the 2009 International Conference on Artificial Intelligence, ICAI 2009
SP - 32
EP - 38
BT - Proceedings of the 2009 International Conference on Artificial Intelligence, ICAI 2009
T2 - 2009 International Conference on Artificial Intelligence, ICAI 2009
Y2 - 13 July 2009 through 16 July 2009
ER -