A Hybrid Genetic Algorithm for Designing Feedforward Neural Networks
In this paper,a hybrid algorithm is proposed fordesigning feedforward neural networks.A genetic al-gorithm is proposed to tune the connections and para-meters between the input layer and the hidden layer,and orthogonal transformation is applied to tune theconnections and parameters between the hidden layerand the output layer.The crossover operator and mu-tation operator are based on the singular value de-composition of the outputs of the hidden nodes.Usingthe proposed algorithm,both the structure and para-meters of a neural network can be optimized efficiently.Simulations are presented to demonstrate the effective-ness of the proposed approach.
JinhuaXu Yue Lu
Department of Computer Sciences,East China Normal University,Shanghai,200241,China
国际会议
厦门
英文
549-554
2008-11-17（万方平台首次上网日期，不代表论文的发表时间）