Chapter 15: Modeling Sequential Data Using Recurrent Neural Networks

Chapter Outline

• Introducing sequential data

  • Modeling sequential data—order matters

  • Representing sequences

  • The different categories of sequence modeling

• RNNs for modeling sequences

  • Understanding the RNN looping mechanism

  • Computing activations in an RNN

  • Hidden-recurrence versus output-recurrence

  • The challenges of learning long-range interactions

  • Long short-term memory cells

• Implementing RNNs for sequence modeling in PyTorch

  • Project one: predicting the sentiment of IMDb movie reviews

    • Preparing the movie review data

    • Embedding layers for sentence encoding

    • Building an RNN model

    • Building an RNN model for the sentiment analysis task

      • More on the bidirectional RNN

  • Project two: character-level language modeling in PyTorch

    • Preprocessing the dataset

    • Building a character-level RNN model

    • Evaluation phase: generating new text passages

• Summary

Please refer to the README.md file in ../ch01 for more information about running the code examples.