Terminus

Machine learning

Recurrent networks and LSTMs

Modelling sequences with recurrence, why gradients vanish, and how LSTMs and GRUs fix it.

About 15 hours of study.

Where to learn it

Read
Dive into Deep Learning

Zhang, Lipton, Li, Smola

Chapters 9–10

Watch
CS224N: Natural Language Processing with Deep Learning

Christopher Manning, Stanford Online

The lectures on language models and RNNs

Practise

No practice set picked yet.

Suggest one

Wrong chapter, dead link, or know something better? Tell us on GitHub.

Before and after

Recurrent networks and LSTMs

Opens up

Nothing else on the map yet.