Sign inSign in
ConceptAI & ML

Zero-shot transfer

The ability of a system to generalize to a new task or environment without prior training on it.
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.

Fluid dynamics simulations1Machine learning models1Reinforcement learning1

Lecturers

2

Each in their own terms, from the easiest level.

  • Steve Brunton

    University of Washington · Graduate

    Applying a reinforcement learning controller trained in a simulation environment directly to a different, more complex simulation or real-world scenario without further modifications or retraining.
    • 10:08HydroGym: A Reinforcement Learning Platform for Fluid Dynamics

Connections

3

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

2 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.