Sign inSign in
ConceptAI & ML

Data augmentation

A technique to increase the diversity of data available for training models, such as by applying random transformations to existing images.
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.

CNNs1Machine learning1Machine learning training data1Regularization1Training data1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    A regularization strategy where input data is randomly transformed during training while preserving the label, introducing stochasticity that is marginalized at test time.
  • Phillip Isola

    MIT · Undergraduate

    Applying transformations to small data that do not fundamentally change the target class to make it bigger.
    • 30:37Hacker's Guide to Deep Learning

Lectures that assume it

3

Connections

14

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

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.