Sign inSign in
ConceptAI & ML

Contrastive learning

A learning technique that maps similar data points to nearby embeddings and dissimilar data points to far-away embeddings.
as Jeremy Bernstein defines itMITThe 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

3

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Undergraduate

    A learning technique that trains a model to map similar data points close together and dissimilar data points far apart in a representation space.
    • 1:15:54Transfer Learning: Models
    • 39:15Transfer Learning: Data
  • Jürgen Cito, Tobias Fiebig & Peter Knees

    TU Wien Informatics · Graduate

    Contrastive learning changes the learning objective via a loss function to maximize similarity of positive examples and minimize similarity of negative examples.
    • 1:25:46Inaugural Lectures: The Future of Software Engineering with AI, Making it Ping, and Digital Humanism

Lectures that assume it

3

Connections

17

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.