Extremal Optimization Combined with LM Gradient Search for MLP Network Learning

Abstract

Gradient search based neural network training algorithm may suffer from local optimum, poor generalization and slow convergence. In this study, a novel Memetic Algorithm based hybrid method with the integration of “extremal optimization” and “Levenberg–Marquardt” is proposed to train multilayer perceptron (MLP) networks. Inheriting the advantages of the two approaches, the proposed “EO-LM” method can avoid local minima and improve MLP network learning performance in generalization capability and computation efficiency. The experimental tests on two benchmark problems and an application example for the end-point-prediction of basic oxygen furnace in steelmaking show the effectiveness of the proposed EO-LM algorithm.

Keywords

• Back propagation; Extremal optimization; “Levenberg–Marquardt” (LM) gradient search; Memetic Algorithms; Supervised learning