ClassroomThe classroom
Back to the lesson libraryMECHANISM · 13 MIN
M13.3 CONNECT THE MECHANISM

Choose what to keep, add, and reveal

The festival started at 7 a.m. Can the model still remember it at 2 p.m.? Compute an LSTM step by hand and see how gates rescue the fading gradient.

LESSON OVERVIEW13 min lesson

Lesson overview

The festival started at 7 a.m. Can the model still remember it at 2 p.m.? Compute an LSTM step by hand and see how gates rescue the fading gradient.

What you’ll explore

  • LSTMs and GRUs use learned gates to control state updates; these mechanisms can help long-range learning but do not provide unlimited or perfect memory.
GO TO THE SOURCE

Original explanations, connected to the research.

Long Short-Term Memory (Hochreiter & Schmidhuber, 1997)Learning to Forget: Continual Prediction with LSTM (Gers, Schmidhuber & Cummins, 2000)Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (Cho et al., 2014)Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling (Chung et al., 2014)Dive into Deep Learning — LSTMDive into Deep Learning — GRU
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.