Research on Optimization Model of Neural Network Based on Genetic Algorithm

Abstract. BP neural network is a multilayer feed-forward network for training according to the error back-propagation algorithm, its main advantage is the strong non-linear mapping ability, but the training of BP neural network is easy to fall into local minima, and slow convergence speed. This paper makes use of the good global search ability of genetic algorithm, for training the connection weights and thresholds of BP neural network, establishment of GA-BP model, effectively compensate slow convergence speed, easy fall into local minimum shortcomings for BP neural network. Through example analysis, verification of the global optimization capability of GA optimization BP neural network has been greatly improved compared with the pure BP neural network model