Sign inSign in
ConceptAI & ML

Test-time training

Adapting or learning with model parameters during inference time rather than only during the initial training phase.
as Andrej Karpathy defines itThe 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.

  • Xi Ye

    Alberta Machine Intelligence Institute (Amii) · Graduate

    Performing parameter updates to learn from new context at test time.
    • 54:40AI Seminar: Actionable Interpretability for Language Model Reasoning
  • Phillip Isola

    MIT · Graduate

    A training approach where a model adapts its weights or behavior during inference to improve performance on specific tasks or sequences.
    • 57:51Inference Methods for Deep Learning

Connections

6

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.