Tuning differential evolution for artificial neural networks

Pedersen, M.E.H. and Chipperfield, A.J. (2011) Tuning differential evolution for artificial neural networks , Nova Science Publishers, 277pp.

Abstract

The efficacy of an optimization method often depends on the choosing of a num-ber of behavioural parameters. Research within this area has been focused on devising schemes for adapting the behavioural parameters during optimization, so as to alleviate the need for a practitioner to select the parameters manually. But these schemes usually introduce new behavioural parameters that must be tuned. This study takes a different approach in which finding behavioural parameters that yield good performance is con-sidered an optimization problem in its own right and can therefore be attempted solved by an overlaid optimization method. In this work, variants of the general purpose op-timization method known as Differential Evolution have their behavioural parameters tuned so as to work well in the optimization of an Artificial Neural Network. The re-sults show that DE variants using so-called adaptive parameters do not have a general performance advantage as previously believed

This record has no associated files available for download.

Contributors

Author: A.J. Chipperfield

Download statistics