Atlas

Foundations

Convolutional Networks

Weight sharing over space: how machines learned to see.

You can jump straight in, but this star assumes Training & Optimization. Not recommended as a first stop.

Four layers of depth

Each layer ends with a quiz. Finish layer 4 and you own this concept.

  1. L1IntuitionWhy images need a different kind of layer than plain fully-connected networks, and what a convolution intuitively does.5m
    40 XP
  2. L2MechanicsThe mechanics of convolution, stride, padding, pooling, and how spatial dimensions shrink through a network.8m
    70 XP
  3. L3CodeImplementing a 2D convolution from scratch and building a small image classifier CNN in PyTorch.12m
    110 XP
  4. L4FoundationsThe math of discrete convolution, output-shape formulas, parameter counting, and translation equivariance.15m
    180 XP

33 stars in the atlas.