In this tutorial, we will use our custom GRU network to classify MNIST handwritten digits, which aims to evaluate the effectiveness of our custom GRU.
In this tutorial, we will introduce how to build our custom GRU network using tensorflow, which is very similar to create a custom lstm network.
There are many models that have improved LSTM, GRU (Gated Recurrent Unit) is one of them. In this tutorial, we will introduce GRU and compare it with LSTM.
As to GRU, there is a reset gate in it. Can we remove this reset gate in GRU? If we remove it, the performance of GRU will decreased? The answer is we can remove the reset gate.
In this tutorial, we will introduce you how to build your own BiLSTM model using tensorflow, you can modify our code and build a customized model.
We have created a customized lstm model (lstm.py) using tensorflow. In this tutorial, we will use this customized lstm model to train mnist set and classify handwritten digits.
In this tutorial, we will use tensorflow to build our own LSTM model, not use tf.nn.rnn_cell.BasicLSTMCell(). You can create a customized lstm by it.
In this tutorial, we list some tips on lstm kernel, which will help you to understand and use lstm in you tensorflow application, you can get more useful information by referring our tutorial.
In this tutorial, we discuss the weights in lstm cell and how to get it. The shape of kernel is very important, which can help us to understand lstm, you can follow our tutorial to more detail.
In this tutorial, we discuss what is adaptive gating mechanism in deep learning and how to use it in ai application, the key is gate is a sigmoid function of inputs. You can learn how to apply it in your research by following our tutorial.