Sign inSign in
ConceptAI & ML

Empirical risk minimization

An optimization principle in machine learning that trains models by minimizing the error on the training dataset.
as Marzyeh Ghassemi defines itUC BerkeleyThe 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

4

Each in their own terms, from the easiest level.

  • Pieter Abbeel

    UC Berkeley · Undergraduate

    The basic principle of machine learning where we find the model that does best on our actual training set since we do not know the true test distribution.
    • 49:12Machine Learning: Naive Bayes
  • Sergey Levine

    UC Berkeley · Graduate

    A training method where a sampled training set is used to give an empirical estimate of the risk, which is then minimized.
    • 30:52Offline Reinforcement Learning
  • Shahar Mendelson

    Texas A&M University · Graduate

    Picking the function in the class that best fits the given sample data.
    • 29:36AI in Science and Engineering: The Role of Academia in Understanding AI

Lectures that assume it

4

Connections

18

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

4 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.