Sign inSign in
ConceptAI & ML

Convolutional layer

Layers that apply the same calculation in translation-invariant ways across different regions of an image using parameter sharing.
as Pieter Abbeel defines itUC BerkeleyThe 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.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Undergraduate

    Convolutional layers are basically the same thing as a linear layer except convolution layers do not apply linear multiplication to the full input, but on overlapping patches of the input.
    • 1:06:11Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm
  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    A layer that applies filters across spatial locations of an input volume using local connectivity and shared parameters to produce an activation map.
    • 50:24Convolutional Neural Networks

Lectures that assume it

6

Connections

17

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.