Crossover-based local search in cooperative co-evolutionary feedforward neural networks

Cooperative coevolution has been a major approach to neuro-evolution. Memetic algorithms employ local search to selected individuals in a population. This paper presents a new cooperative coevolution framework that incorporates crossover-based local search. The proposed approach effectively makes use of local search without adding to the computational cost in the sub-populations of cooperative coevolution. The relationship between the intensity of, and interval between the local search is empirically investigated and a heuristic for the adaptation of the local search intensity during evolution is presented. The method is used for training feedforward neural networks on eight pattern classification problems. The results show an improved performance in terms of optimisation time, scalability and robustness for most of these problems.

Figure optionsDownload as PowerPoint slideHighlights
► We present a memetic cooperative coevolution framework that employs crossover-based local search.
► The framework is used for evolving feed-forward networks for pattern classification problems.
► The results show that the proposed approach shows improvement in terms of optimisation time, scalability and robustness.