Convolutions

How networks see edges

An interactive lesson with 6 steps, about 5 minutes: you predict, drag and solve, with instant feedback on every answer. It runs in your browser and needs JavaScript.

What you’ll learn

• A convolution slides a small filter over the image, computing a weighted sum at each position.
• Shared weights: few parameters, and features are detected anywhere in the image.
• Stacked layers build edges into textures, parts and whole objects.

Steps

1. Too many weights
2. Sliding a filter
3. Try some filters
4. One output pixel
5. Layers of features
6. Shared weights