1、TensorFlow官网地址：https://www.tensorflow.org/tutorials/recurrent

2、内容讲解：

   (1) Recurrent neural networks tutorial: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/  Denny的内容深入浅出，RNN的入门教材，讲解了基本RNN的架构，之后讲了LSTM和GRU，其中LSTM是引用网站（3）的内容，遗憾的是文中的完整版代码使用Theno实现的，而不是TensorFlow

   （2） RNNs in TensorFlow, a practical guide and undocumented features: http://www.wildml.com/category/neural-networks/recurrent-neural-networks/ WildML的另一个RNN学习资料

   （3） Understand LSTM Networks: http://colah.github.io/posts/2015-08-Understanding-LSTMs/  这个网站的讲解深入浅出，非常适合LSTM初学者，被多个网站引用，被称为是学习LSTMs的great article。讲解了RNN的原理，以及2016年前存在的RNN。遗憾的是没有实例和代码

    (4) Introducation to RNN in TensorFlow https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/ 文中列举两个应用： sequence classification and sequence labeling

   Attention and Augmented RNNs: http://distill.pub/2016/augmented-rnns/

   (5) Creating a text generator using LSTM: https://chunml.github.io/ChunML.github.io/project/Creating-Text-Generator-Using-Recurrent-Neural-Network/   Tensorflow-keras

   (6) Movie sentiment classification using LSTM: http://machinelearningmastery.com/sequence-classification-lstm-recurrent-neural-networks-python-keras/   Tensorflow-keras

3、https://danijar.com/variable-sequence-lengths-in-tensorflow/

5. RNN Example using Pytorch

   http://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html#the-encoder