Tree LSTM model is widely used in many deep learning fields. It is often used to process tree structure data. In this tutorial, we will introduce it for deep learning beginners.
In order to improve the performance of lstm model in deep learning, we can use stacked lstm. In this tutorial, we will introduce the stacked lstm for deep learning beginners.
To improve lstm and bilsm, you should implement them by your own tensorflow code. In this tutorial, we will discuss why the performance of your custom lstm or bilstm model are worse than tf.nn.dynamic_rnn() and tf.nn.bidirectional_dynamic_rnn().
In this tutorial, we will introduce how the tf.nn.bidirectional_dynamic_rnn() process variable length sequence, which is very useful to help you understand this function and build your custom model.
Nested LSTM network is one of improved LSTM model, which has better performance than classic LSTM. In this tutorial, we will introduce it for lstm network beginners.
LSTM network contains three gates: input gate, forget gate and output gate. In this tutorial, we will discuss the effect of each gate in LSTM.
In this tutorial, we discussed the difference of LSTM and GRU performance and tell you which network you should choose for deep learning programming.
LSTM peephole conncections is one of improvements for classic LSTM network. In this tutorial, we will introduce the difference between LSTM peephole conncections and classic LSTM.
In this tutorial, we discuss how LSTM Weight and Bias are initialized when initializer is None in TensorFlow. We can modify our custom lstm to make its performace same to tensorflow LSTM network.
In this tutorial, we introduce why we should add a forget bias for lstm forget gate and add a forget bias for our custom lstm network.