TensorFlow 中的所有反向传播都是通过自动微分网络前向传播中的操作，并添加显式操作来计算网络中每个点的梯度.一般实现可以在<.gradients>，但使用的特定版本取决于你的 LSTM 是如何实现的:

All backpropagation in TensorFlow is implemented by automatically differentiating the operations in the forward pass of the network, and adding explicit operations for computing the gradient at each point in the network. The general implementation can be found in tf.gradients(), but the particular version used depends on how your LSTM is implemented:

• 如果 LSTM 被实现为有限时间步长的展开循环，通常的方法是通过时间截断反向传播，它使用 tf.gradients() 中的算法来构建展开的反向传播反方向循环.
• 如果 LSTM 实现为 tf.while_loop()，它会使用额外的支持来区分 control_flow_grad.py.

• If the LSTM is implemented as an unrolled loop for a finite number of timesteps, the usual approach is truncated backpropagation through time, which uses the algorithm in tf.gradients() to build an unrolled backpropagation loop in the opposite direction.
• If the LSTM is implemented as a tf.while_loop(), it uses additional support for differentiating loops in control_flow_grad.py.