Sign inSign in
ConceptAI & ML

Long short-term memory

A specific type of RNN architecture designed to learn long-term dependencies by using gating mechanisms to control information flow.
as Sara Beery defines itMITThe wording closest to all 3 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Lecturers

3

Each in their own terms, from the easiest level.

  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    A specialized RNN architecture designed to alleviate vanishing and exploding gradients by introducing a cell state and gating mechanisms.
    • 55:48Recurrent Neural Networks
  • Ava Amini

    MIT · Undergraduate

    A type of recurrent neural network unit that uses gates to selectively add or remove information to track long-term dependencies.
    • 37:03Recurrent Neural Networks, Transformers, and Attention

Connections

5

The lectures that define it or assume it, and the concepts next to it.

Concepts2

Lectures3

3 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.