Chapter 9. Deep learning for sequences and text
This chapter covers
- How sequential data differs from nonsequential data
- Which deep-learning techniques are suitable for problems that involve sequential data
- How to represent text data in deep learning, including with one-hot encoding, multi-hot encoding, and word embedding
- What RNNs are and why they are suitable for sequential problems
- What 1D convolution is and why it is an attractive alternative to RNNs
- The unique properties of sequence-to-sequence tasks and how to use the attention mechanism to solve them
This chapter focuses on problems involving sequential data. The essence of sequential data is the ordering of its elements. As you may have realized, we’ve dealt with sequential data before. ...
Get Deep Learning with JavaScript now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
