Co-operating Populations with Different Evolution Behaviours

Abstract

Parallel genetic algorithms (PGA) offer a natural and productive way to solve a problem better than a single population. Up to now the different PGA paradigms use the same evolution behaviour on each population. This paper proposes a method, called Co-operating Populations with Different Evolution Behaviours (CoPDEB) where the populations are allowed to exhibit different evolution behaviours. This is achieved by using a variety of selection mechanisms, operators, communication methods and parameters as it is explained in the sequel. This method has been tested on the problem of training a recurrent artificial neural network (RANN)