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.
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.
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 oneThe 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.