Tuning Dierential Evolution For Articial Neural Networks
Magnus Erik, Hvass Pedersen, Andrew John Chippereld · 2008
The ecacy of an optimization method often depends on the choosing of a number 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 dierent approach in which nding behavioural parameters that yield good performance is considered 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 optimization method known as Dierential Evolution have their behavioural parameters tuned so as to work well in the optimization of an Articial Neural Network. The results show that DE variants using so-called adaptive parameters do not have a general performance advantage as previously believed.