An adaptive fractional-order BP neural network based on extremal optimization for handwritten digits recognition

Abstract

The optimal generation of initial connection weight parameters and dynamic updating strategies of connection weights are critical for adjusting the performance of back-propagation (BP) neural networks. This paper presents an adaptive fractional-order BP neural network abbreviated as PEO-FOBP for handwritten digit recognition problems by combining a competitive evolutionary algorithm called population extremal optimization and a fractional-order gradient descent learning mechanism. Population extremal optimization is introduced to optimize a large number of initial connection weight parameters and fractional-order gradient descent learning mechanism is designed to update these connection weight parameters adaptively during the evolutionary process of fractional-order BP neural network. The extensive experimental results for a well-known MNIST handwritten digits dataset have demonstrated that the proposed PEO-FOBP outperforms the original fractional-order BP neural network and the traditional integer-order BP neural network in terms of training and testing accuracies.