Learn AI0112 lessons
How does a network learn?
Start with a single neuron. Discover how small numerical steps become learning.
0 completedView lessons
CHOOSE WHAT TO LEARN
Courses
Build your understanding through explanations, experiments and projects. Follow a course or jump to a topic you want to learn.
Browse a course
From numerical building blocks to your first model.7 modules
0213 lessons
What has the network learned?
Look inside learned features and find the shortcuts that can fool a model.
0 completedView lessons
0313 lessons
How does AI process language?
Follow a word from a numerical representation to a next-token prediction.
0 completedView lessons
048 lessons
Why does AI need computation?
Understand the tradeoffs between model size, data, and computation.
0 completedView lessons
0510 lessons
Data audits and training diagnosis
Repair an evaluation pipeline and diagnose a training failure, with separate project assessments.
0 completedView lessons
0610 lessons
Simple models and useful baselines
Compare neighbors, fitted trees, numerical regression and class probabilities with simple references before adding complexity.
0 completedView lessons
078 lessons
Generative models beyond text
Learn reconstruction, latent representations and the limits of sampling from small trained models.
0 completedView lessons
Perception workbench: train, stress-test and report — saved evidence and separate objective cases; implementation review pending.
UNDERSTAND NEURAL NETWORKS · PROJECT
Build a classifier you can explain.
Train a small network, compare validation results, freeze a test evaluation, and write a model card.
Start the classifier projectA fresh start is a good start.
Brush up on the basics, or jump straight in. We’ll meet you where you are.
Review the basics