tensorflow - 反向传播和反向模式自动微分有什么区别？

Question

经历这个book ，我熟悉以下内容:

For each training instance the backpropagation algorithm first makes a prediction (forward pass), measures the error, then goes through each layer in reverse to measure the error contribution from each connection (reverse pass), and finally slightly tweaks the connection weights to reduce the error.

但是我不确定这与 TensorFlow 的反向模式自动差异实现有何不同。

据我所知，反向模式自动微分首先向前遍历图表，然后在第二遍中计算输出相对于输入的所有偏导数。这与传播算法非常相似。

反向传播与反向模式自动差分有何不同？

Answer 1

感谢 David Parks 的回答，提供了有效的贡献和有用的链接，但是我已经找到了本书作者本人对这个问题的答案，这可能会提供更简洁的答案:

Bakpropagation refers to the whole process of training an artificial neural network using multiple backpropagation steps, each of which computes gradients and uses them to perform a Gradient Descent step. In contrast, reverse-mode auto diff is simply a technique used to compute gradients efficiently and it happens to be used by backpropagation.