论文信息 - A hybrid genetic algorithm for training neural networks

A hybrid genetic algorithm for training neural networks

Abstract In this paper a hybrid algorithm for training neural networks is presented. It is a combination of a genetic algorithm and a variant of backpropagation. It is shown through extensive simulation that the presented hybrid scheme exhibits very good convergence properties and in any case much better than those of back propagation.

[1] Bernard Widrow,et al. 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[2] Tom Tollenaere,et al. SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.