An Improvement and Application of Genetic BP Neural Network

Reasonable network structure can obviously improve the learning speed and generalization ability of BP network. In this paper, an improved method to determine the number of hidden layer neurons is proposed. The method mainly takes the theory of linear correlation analysis to delete the redundant nodes and assign the weights related to others. What´s more, genetic algorithm is used to optimize the weights and threshold before linear analysis. The paper constructs the genetic BP network with the influence factors of public bike demand as input and the total demand as output, and applies the improved method to the model. The result shows that the improved algorithm can obviously reduce the number of iterations and training time, and improve the learning speed and generalization ability of the network.