As for the inadequate of BP neural network, PSO algorithm is used for its optimization, thus creating a hybrid neural network model for flood forecasting.
针对BP神经网络的不足,采用P SO算法对BP神经网络进行优化,建立一个混合的神经网络洪水预测模型。
The particle swarm optimization(PSO) algorithm, is used to train neural network to solve the drawbacks of BP algorithms which is local minimum and slow convergence.
针对多层前馈网络的误差反传算法存在的收敛速度慢,且易陷入局部极小的缺点,提出了采用微粒群算法(PSO)训练多层前馈网络权值的方法。
And, in FNN weight training, improved PSO in the convergence rate and the ability to jump out to local optimum algorithm is better than BP.
且改进的粒子群算法在模糊神经网络权值的训练中收敛速度和跳出局部最优的能力都要比BP算法更优。
应用推荐