Python Deep Learning Projects

RNN architectures

We will mostly use the LSTM cell, since it has proven better in most NLP tasks. The principle benefit of the LSTM in RNN architectures is that it enables model training over long sequences, while retaining memory. To solve the gradient problem, LSTMs include more gates that effectively control access to the cell state.

We've found that Colah's blog post (http://colah.github.io/posts/2015-08-Understanding-LSTMs/) is a great place to go to obtain a good understand the working of LSTMs.

These small LSTM units of RNN can be combined in multiple forms to solve various kinds of use-cases. RNNs are quite flexible in terms of combining the different input and output patterns, as follows:

• Many to one: The model takes a complete ...