Sign inSign in
ConceptAI & ML

Batch normalization

A technique that explicitly normalizes layer activations to have a zero mean and unit variance over a mini-batch.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe wording closest to all 5 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.

  • Andrej Karpathy

    Undergraduate

    A neural network layer that normalizes activations across a batch and uses running means and variances tracked via momentum updates during training.
    • 40:50Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm
    • 3:35Building makemore Part 5: Hierarchical Dilated Causal Convolutions (WaveNet)
  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    • 7:26Training Neural Networks II
  • Ali Rahimi

    Google Research & TechTalks · Graduate

    A technique to normalize layer inputs in a neural network to speed up training and reduce internal covariate shift.
    • 17:09Are Deep Neural Networks an Alchemy?

Lectures that assume it

4

Connections

19

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.