Sequences, RNNs and LSTM Memory

3 min
Audience
ages 10–15
Duration
30 to 40 min
Adventure
6/8
Badge to earn
Sequence Keeper

Today's mission

Simulate a recurrent hidden state and explain what the gates of an LSTM try to preserve.

Proof of success: explain "Sequences, RNNs and LSTM memory", complete "The Traveling Card" and name the limit of the analogy.

The story

Eliott reads "The chest is near the lighthouse. Later, it's opened." To link "it" back to the chest, a sequential model must carry context. An RNN updates a hidden state token after token by reusing the same parameters. Over long distances, the gradients can vanish or explode. An LSTM's gates then learn to forget, write and expose part of a cell state.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Language” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one