论文部分内容阅读
提出了一种基于神经网络的电力通信网风险评估算法——基于二分法的学习速率自适应BP(back propagation)神经网络算法.该算法在网络训练过程中使用二分法调整学习速率,使得学习速率在训练过程中不断向最优化方向自动调整.仿真结果表明,收敛速度、误差精度和训练时间等算法性能得到了优化.
This paper proposes a BP neural network based risk assessment algorithm for power communication network - a bisection-based BP neural network (BP) learning algorithm which uses dichotomy to adjust the learning rate in the network training process so that the learning rate In the process of training, the optimization direction is adjusted automatically.The simulation results show that the performance of algorithm such as convergence speed, error precision and training time are optimized.