获得的值与对应的期望值对比,误差使用反传学习算法传回网络,用以更新连接权值。
Compared obtained value with corresponding expected value, error was sent to network with reverse learning algorithm, so that renovate connect weighting value.
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。
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.
应用推荐