Intermediate

A little maths, a lot of intuition.

This free intermediate AI course explains how machine learning actually works, with light maths and lots of pictures. In 14 short lessons you'll see how models learn by gradient descent, how to tell if a model is any good, and the classic architectures behind images, text and recommendations.

Each lesson you finish lights a star.

  1. Lines and curves: regressionThe humble straight line is the ancestor of every neural network. Linear and logistic regression, explained.6 min · 2 quick checks
  2. Gradient descent: rolling downhillHow models find good weights: feel the slope, take a small step down, repeat.6 min · 2 quick checks
  3. Overfitting & the Goldilocks modelToo simple misses the pattern, too complex memorises the noise. How to land just right.5 min · 2 quick checks
  4. Is my model any good?Accuracy can lie. Meet the confusion matrix, precision, recall and F1.6 min · 2 quick checks
  5. Backpropagation: blame, passed backwardsHow a network with millions of weights figures out which ones to adjust.6 min · 2 quick checks
  6. Seeing and remembering: CNNs & RNNsSpecial network shapes for images and sequences, and why they mattered.7 min · 2 quick checks
  7. Embeddings: meaning as mapsHow AI turns words, images and songs into points in space where closeness means similarity.5 min · 2 quick checks
  8. How we test language modelsBenchmarks, leaderboards, human votes and AI judges: how anyone decides one model is better than another, and why it's harder than it looks.7 min · 2 quick checks
  9. Seeing and hearing: multimodal modelsHow one model can read a photo, listen to speech and answer in words: everything becomes tokens.6 min · 2 quick checks
  10. Open-weight models and running AI yourselfWhat "open" really means for AI models, why it matters, and how a laptop can run a capable chatbot.6 min · 2 quick checks
  11. Decision trees and random forestsNewA game of twenty questions that learns from data, and why a whole forest of them still beats neural networks on spreadsheets.7 min · 2 quick checks
  12. Finding groups: clusteringNewHow a computer can sort things into groups when nobody has told it what the groups are, with k-means step by step.6 min · 2 quick checks
  13. How text becomes tokensNewLanguage models don't read letters or words: they read tokens. How text gets chopped up, and why it explains some odd model mistakes.7 min · 2 quick checks
  14. How recommendations workNew"Because you watched...": how apps guess what you'll like next, from similar users to embeddings, and the loops that can narrow what you see.7 min · 2 quick checks
Read it offline

Save all of the Intermediate level on this device for flights, trains and bad Wi-Fi.

Questions about the intermediate level

What should I know before the intermediate level?

Just the ideas from the Beginner level: what AI and machine learning are and how chatbots work. Maths is kept light, and optional Python examples run in your browser.

Is this a free machine learning course?

Yes. Every lesson, quiz and interactive explainer is free with no sign-up, and each lesson links to the free open courses it builds on, like Google's Machine Learning Crash Course and fast.ai.

How long does the intermediate level take?

Most lessons take six to eight minutes, so about two weeks at one lesson a night.