Abstract:
In this paper, parallel differential evolution
algorithm with multiple trial vectors for training
artificial neural networks (ANNs) is presented. The
proposed method is PDEA, which is a DE-ANN+
modified by adding island model. Within PDEA, an
island model is designed to cooperatively search for
the global optima in search space. By combining the
strengths of the differential evolution algorithm with
multiple trial vectors and island model, PDEA greatly
improves the optimization performance. PDEA
algorithm is used for ANN training to classify the
parity-p problem. Results obtained using proposed
algorithm has been compared to the results obtained
using other evolutionary algorithms.
