Improved BP Neural Network Algorithm Model Based on Chaos Genetic Algorithm

Genetic algorithm has been successfully applied to complexity problems of real-world. But the genetic algorithm is easy to be premature convergence, and full into local optimum. For the ergodicity of chaotic theory is adopted to genetic algorithm optimization, we put forward the improved chaos genetic algorithm. In order to avoid the slow convergence speed and local optimal problems of BP neural network, we improve the weights and thresholds of BP neural network, on the basis of the improved chaos genetic algorithm and BP neural network. After the training, the BP neural network is of high accuracy and fast convergence. The example analysis and simulation prove that the BP neural network optimized by chaotic genetic algorithm has high calculation accuracy and strong convergence.