BP算法是训练前馈神经网络最著名的算法之一,它允许通过向前和向后的反馈来更新权重,直到误差函数保持在局部最小值。
BP algorithm is one of the most famous algorithms for training a feed forward neural net , it allows to update weights by moving forward and backword until the error function stuck at its local minimum.
在这段代码中,我们一步一步地解释如何用BP算法训练神经网络,并提供相关的描述功能。
In this code we explain step by step in comments how we can train a neural net with BP algorithm with additional illustrative features.
作者电子邮箱 : berghouttarek@gmail;com
更多精彩文章请关注公众号: