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.

youdao

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.

youdao