The optimum programs are made for the target error, the learning of Neural Network, the time of training.

对目标误差、网络的学习率和训练次数进行了具体的优化。

youdao

Because the error transfer function of rough neural network is not differentiable, genetic algorithms are applied for training the network.

由于粗神经网络的误差传递函数不可微，所以采用遗传算法来训练粗神经网络。

youdao

It can identify the parameters of a controlled object by forming a fake output and bring in a feedback error for performing an on-line training to decouple the neural network.

它通过构造伪输出辨识被控对象参数，引进反馈误差，实现对解耦神经网络的在线训练。

youdao