Observed arrival · 2026-11-05
Receptive Field: CNNs, One Idea at a Time
An interactive guide that teaches convolutional neural networks through short chapters, draggable figures, worked examples, and questions.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People learning convolutional neural networks
- Worth noticing
- The nine-chapter outline includes checkerboard artifacts, backpropagation, and a final chapter on what the network learned.
Field notes
The course outline gives four modules to each of nine chapters, with a progress display tracking modules and chapters separately. Topics include how parameter counts change when an image is flattened, how stride and padding affect output size, and where gradients go during convolutional backpropagation. The homepage links to a separate receptive-field calculator and identifies Nico Bonetto as the author.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue