Its learning rule is to use the steepest descent method, by back-propagation network to continuously adjust the weights and thresholds, so the network and the minimum sum of squared errors.
它的学习规则是使用最速下降法，通过反向传播来不断调整网络的权值和阈值，使网络的误差平方和最小。
youdao
应用推荐
模块上移
模块下移
不移动