USP Electronic Research Repository

Memetic Cooperative Co-evolutionary Recurrent Neural Networks

Chandra, Rohitash and Frean, M. and Zhang, M. (2011) Memetic Cooperative Co-evolutionary Recurrent Neural Networks. Soft Computing, N/A . N/A-N/A. ISSN 1432-7643

Full text not available from this repository. (Request a copy)

Abstract

Adaptation during evolution has been an
important focus of research in training neural networks.
Cooperative coevolution has played a significant role in
improving standard evolution of neural networks by organizing
the training problem into modules and independently
solving them. The number of modules required to represent
a neural network is critical to the success of evolution. This
paper proposes a framework for the adaptation of the
number of modules during evolution. The framework is
called adaptive modularity cooperative coevolution. It is
used for training recurrent neural networks on grammatical
inference problems. The results shows that the proposed
approach performs better than its counterparts as the
dimensionality of the problem increases.

Item Type: Journal Article
Subjects: Q Science > Q Science (General)
Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Repo Editor
Date Deposited: 14 May 2015 23:33
Last Modified: 14 May 2015 23:33
URI: https://repository.usp.ac.fj/id/eprint/7979

Actions (login required)

View Item View Item