Optimization of Weights in Neural Networks Based on Genetic Algorithm

Aimed at the shortcomings of the BP algorithm,such as low efficiency of study,slow speed of convergence,easy to be trapped into local optimums,etc,this paper introduces Genetic Algorithm (GA) -a new algorithm based on natural selection and the principle of gene genetics, and discusses its weights optimizing in BP neural networks. The simulation results show that GA can improve the convergence speed effectively and avoid the trap of local optimums.