深入浅出BP（BackPropagation）反向传播算法

持续更新：

一、什么是BP算法

1.1 维基定义：

Backpropagation is a method used in artificial neural networks to calculate the error contribution of each neuron after a batch of data (in image recognition, multiple images) is processed. This is used by an enveloping optimization algorithm to adjust the weight of each neuron, completing the learning process for that case.
(https://en.wikipedia.org/wiki/Backpropagation)

1.2 用途

二、BP算法的前世今生

2.1 前向传播

2.2

三、BP算法的原理与数学推导

四、BP算法的python实现

五、BP算法在TensorFlow下的实现

参考文献

[1].
[2].
[3].