Sign inSign in
ConceptAI & ML

Regularization

Adding a term or constraint to the loss function to prevent a model from overfitting to training data.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe wording closest to all 13 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

6

Each in their own terms, from the easiest level.

  • Yaser Abu-Mostafa

    Caltech · Undergraduate

    A technique used to constrain model complexity and combat overfitting.
  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    • 28:18Loss Functions and Optimization
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    Regularization keeps a large hypothesis space but avoids weird parts of that space where overfitting is likely.
    • 1:09:31Machine Learning: Naive Bayes
    • 40:53Machine Learning: Neural Networks and Decision Trees
  • Stephen Boyd

    Stanford University · Undergraduate

    Regularization balances objectives like tracking error against penalties on input magnitude and variation in optimization problems.
    • 28:24Applications of Singular Value Decomposition in LDS and Electrical Engineering
    • 40:27Approximation and Fitting
  • Andrej Karpathy

    Undergraduate

    Augmenting the loss function with a small component called regularization loss to incentivize weights to be near zero.
    • 1:51:59Spelled-Out Intro to Language Modeling: Building makemore (Bigram & Cross-Entropy)
  • Brian Yu

    Harvard University · Undergraduate

    The process of penalizing hypotheses that are more complex in order to favor simpler, more general hypotheses.
    • 8:14:45Harvard CS50’s Artificial Intelligence with Python – Full University Course

Lectures that assume it

18

The first 12 are shown.

Connections

40

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

Concepts9

Show 3 more

Lectures31

Show 25 more

6 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.