Your browser doesn't support speech here. You can still read everything, or try Chrome, Edge or Safari.
Course 3 of 10 · Beginner → Intermediate
Maths for AI
The maths behind the models, visually. Notation, vectors and matrices, derivatives and gradients, probability and statistics, eigenvectors, optimisation, information theory and numerical stability, each with interactive pictures.
How this course works
Welcome
- Level: Beginner → Intermediate. You need: School algebra. Python helps for the code examples.
- Scared of maths? Every idea comes with a picture you can drag and a few lines of NumPy that check it. Read the words first; the symbols come second.
- Start with Reading ML Maths: it explains every symbol the rest of the course uses.
- Pick a topic from the sidebar; they go in order. Press ▶ Play this topic to hear a lesson read aloud, or 🔊 Explain on one section.
- Topics climb from Beginner to Intermediate · Maths, Advanced and Code; use the Show chips to hide levels you don't need. Most have a Watch it animation, Try it demos and runnable code examples, and every topic ends with a quiz: answer it to mark the topic done ✓.
- Stuck? Press 💬 Ask the AI tutor: a small free AI model that runs on your own device and answers from the course.
- Progress is saved in this browser and shared across all the courses on this site.
Learning path: 🐍 Python → 🗄️ SQL & Databases → ∑ Maths for AI → 📈 Machine Learning → 🧠 Deep Learning → 👁️ Computer Vision → 💬 Natural Language Processing → ✨ Generative AI & LLM Apps → 🚀 Flask & Deployment → 🔬 Becoming an AI Researcher
Getting started
Refreshers: school maths you will need
2. Refresher: Numbers, Powers & AlgebraThe school maths every later lesson assumes, explained from scratch: the order of operations, negative numbers, fractions, decimals and percentages, powers and roots, scientific notation, and rearranging an equation to find an unknown.3. Refresher: Functions & GraphsWhat a function is (a rule from inputs to outputs), reading and sketching graphs, straight lines and their slope, curves such as x², exponential growth and decay, and logarithms as the reverse of powers.4. Refresher: Describing Data with NumbersSummarise a list of numbers: the mean, median and mode, why outliers pull the mean, spread (range, variance and standard deviation), percentiles and quartiles, and reading a histogram. These are the first things you compute on any dataset.
Notation & functions
Linear algebra
6. Vectors, Norms & the Dot ProductData points are vectors; predictions are dot products.7. Matrices & Matrix MultiplicationA dataset is a matrix; a layer of a neural net is a matrix multiply.8. Eigenvectors, Covariance & SVDThe linear algebra behind PCA, conditioning and convexity.
Calculus & optimisation
9. Derivatives & the Chain RuleSlopes tell a model which way to adjust its weights.10. Partial Derivatives, Gradients & the HessianCalculus with many weights at once.11. Optimisation: Minima, Convexity, Taylor & LagrangeThe maths of finding the best parameters.
Probability & statistics
12. Probability & DistributionsThe language of uncertainty, noise and predictions.13. Likelihood, MLE & MAPHow "fit the data" becomes a precise mathematical recipe.14. Statistics for Decisions: Intervals, Tests & A/BSampling variation, confidence intervals, hypothesis tests, p-values, power and sample size, and how to run an A/B test without fooling yourself.
Information & computation
15. Information Theory: Entropy, Cross-Entropy & KL DivergenceMeasure surprise and uncertainty in bits, see why cross-entropy is the loss function of classifiers and language models, and compare distributions with KL divergence.16. Floating Point & Numerical StabilityHow computers store real numbers, why 0.1 + 0.2 is not 0.3, overflow and underflow, the stable softmax and log-sum-exp tricks, working with log-probabilities, and what float16 and bfloat16 change when training large models.
Checkpoint
When you finish