Sign inSign in
ConceptAI & ML

Dropout

A regularization technique that randomly shuts off a subset of neurons during training to prevent overfitting.
as Andrej Karpathy defines itThe wording closest to all 6 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

5

Each in their own terms, from the easiest level.

  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    Randomly setting a subset of neuron activations to zero in each forward pass during training.
    • 55:44Training Neural Networks II
    • 2:46Deep Learning Software
  • Patrick Winston

    MIT · Undergraduate

    A technique where neurons are randomly dropped out on every iteration to prevent the network from getting stuck in local maxima.
    • 36:56Deep Neural Networks: MIT Artificial Intelligence
  • Brian Yu

    Harvard University · Undergraduate

    Temporarily removing units selected at random from a neural network during training to prevent over-reliance on certain units.
    • 9:42:30Harvard CS50’s Artificial Intelligence with Python – Full University Course
  • Gilbert Strang

    MIT · Undergraduate

    A regularization technique where a careful subset of data or neuron outputs is dropped out during training to reduce overfitting.
    • 4:36ImageNet and Convolutional Neural Networks

Lectures that assume it

1

Connections

15

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

5 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.