论文部分内容阅读
分析了 BP神经网络的缺陷和遗传算法的特点 ,提出了基于遗传算法的 BP神经网络模型算法 ,该算法利用遗传算法全局寻优能力强等特点 ,可克服神经网络易陷入局部极小值、训练速度慢的缺陷。仿真结果表明 :遗传算法和神经网络相结合的算法具有较好的全局快速收敛等性能。
The defects of BP neural network and the characteristics of genetic algorithm are analyzed. A BP neural network model algorithm based on genetic algorithm is proposed. This algorithm utilizes the advantages of global optimization ability of genetic algorithm to overcome the difficulty of neural network falling into local minimum and training Slow defects. The simulation results show that the algorithm combining genetic algorithm and neural network has good performance of global fast convergence.