TwiddleLab / Courses / Artificial Intelligence

How Machines See and Hear

Pictures and sounds become grids of numbers. Watch filters find edges.

Intermediate · 10 lessons · Free, no account needed

Best after: How a Neural Network Thinks, Learning From Data

Start the course

Lessons

1. A Picture Is a Grid of Numbers (5 min): A digital picture is a grid of pixels, and each pixel is stored as a number.
2. Filters Find Edges (7 min): A filter (or kernel) is a tiny grid of numbers, like 3 × 3.
3. Stacking Filters: Convolution Layers (7 min): A convolution layer is a set of filters that turns one stack of maps into a new stack of maps.
4. Pooling: Zooming Out (7 min): Max pooling cuts a feature map into 2 × 2 blocks and keeps only the biggest number in each.
5. Filters Learn Themselves (7 min): In a real network nobody writes the filters. They start as random numbers and training adjusts them: learned filters.
6. Reading Digits (7 min): A convolutional network (CNN) stacks filters, pooling and a final layer that weighs everything into one score per answer.
7. Fooling a Vision Model (7 min): An adversarial example is an input changed on purpose, often by a tiny amount, so a model gets it wrong.
8. Sound Is a Picture Too (7 min): A microphone measures air pressure thousands of times a second. Each measurement is a sample; how many per second is the sample rate.
9. Faces, Cameras and Fairness (7 min): A face network turns each photo into a face embedding: a list of numbers, a point. Photos of one person land close together.
10. Project: Teach It to See Critters (8 min): A vision project is a loop: choose the classes, label photos, train, test on new photos, study the misses, add better data.

Lessons are interactive and need JavaScript. Turn it on to play them.