Sign inSign in
ConceptAI & ML

Backpropagation through time

The standard backpropagation algorithm applied to recurrent neural networks unrolled across all time steps of a sequence.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe wording closest to all 4 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.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Undergraduate

    A training algorithm for recurrent neural networks that involves unrolling the network over a fixed number of time steps and applying standard backpropagation.
    • 18:50Architectures: Memory
  • Ava Amini

    MIT · Undergraduate

    An algorithm for training recurrent neural networks by backpropagating loss through each individual time step across all time steps in a sequence.
    • 31:08Recurrent Neural Networks, Transformers, and Attention
  • Sergey Levine

    UC Berkeley · Graduate

    Gradient-based training of recurrent neural networks across multiple time steps.
    • 11:33Model-Based Reinforcement Learning with Policies

Connections

7

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

4 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.