Training

Structured, gamified learning paths. Earn XP as you go and reach 90% mastery to unlock the next stage.

Not sure where to start?

Answer a few questions and get a guided study plan matched to your goal, or begin with the Foundations paths below.

Run real code in your lessons

Many lessons include live Python cells powered by numpy and scipy, running right in your browser. Edit the code and run it, no install required. The first lesson of every path is free to try.

Try a live lesson

Foundations

Probability and Statistical Foundations

Reason about uncertainty precisely, then meet the central problem of learning from data: separating the error you can remove from the error you cannot.

5 modules: 5 modules
Total XP: 540 XP
Mastery gate: 90% to advance

Foundations

Search and Heuristics

The oldest working idea in artificial intelligence: describe a problem as states and actions, then let a systematic exploration find the path. Which strategy you pick decides whether the answer is optimal, and whether you run out of memory before you find it.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Foundations

Constraint Satisfaction

Describe a problem as variables, domains and constraints, and a general solver can attack it without knowing what it is about - provided you let it reason about the constraints instead of only guessing values.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Supervised Machine Learning

Derive the workhorse supervised methods rather than merely calling them: least squares, logistic regression, shrinkage penalties, and tree ensembles.

4 modules: 4 modules
Total XP: 500 XP
Mastery gate: 90% to advance

Intermediate

AI Search and Game Theory

Deciding what to do when another agent is deciding too: optimal play against an adversary, pruning the search, and equilibrium when interests only partly conflict.

2 modules: 2 modules
Total XP: 260 XP
Mastery gate: 90% to advance

Intermediate

Deep Learning Foundations

What a neural network actually computes, how the chain rule delivers every gradient in one backward sweep, and why convolution is the right prior for an image.

3 modules: 3 modules
Total XP: 400 XP
Mastery gate: 90% to advance

Intermediate

Logic and Knowledge Representation

The other tradition in artificial intelligence: representing what a system knows as sentences that are true or false, and deriving what must follow - with guarantees a learned model cannot offer.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Unsupervised Learning

Find structure in data that has no response to predict, and face the consequence squarely: with no y there is no held-out error, so every choice you make has to be defended some other way.

3 modules: 3 modules
Total XP: 300 XP
Mastery gate: 90% to advance

Intermediate

Probabilistic Reasoning with Bayesian Networks

Represent a joint distribution over many variables with a graph and a handful of small tables, then answer queries against it exactly when the structure allows and by sampling when it does not.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Support Vector Machines

Classify by choosing the widest slab that separates two classes, then relax it so a few points may sit inside, and finally bend it without ever building the space it is bent in.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Moving Beyond Linearity

Keep least squares and change what you regress on: fixed basis functions buy curvature, constraints buy smoothness, and a penalty buys a curve that chooses its own flexibility.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Making Decisions under Uncertainty

Combine what you believe with what you want: expected utility as the criterion, the curve that explains why sensible people refuse favourable bets, and a price for information that is zero unless it changes your mind.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Classical Planning

Describe actions by what they change and a solver can read the description itself: the same schemas that define the problem also generate the heuristics that solve it, which is something no black-box search can offer.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Learning Probabilistic Models

When the data are complete, learning a probability model is counting - the derivative of the log likelihood does the rest. When variables are hidden there is nothing to count, and the repair is to guess the counts, refit, and repeat until the likelihood stops rising.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Classification Methods Compared

There is one classifier no method can beat, and it needs the answer to build. Everything else - nearest neighbours, discriminant analysis, logistic regression - is a different guess at what it would have done, and the guesses fail in different directions.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Optimization for Learning

Every model on this site is fitted by the same loop: look at the slope, take a step. What decides whether that loop converges in forty steps or diverges in three is not the model - it is curvature, noise, and the size of the step. All three are measurable before the first epoch runs.

3 modules: 3 modules
Total XP: 300 XP
Mastery gate: 90% to advance

Intermediate

Statistical Inference

What a sample can and cannot tell you about the population behind it: how an estimator misses, what a confidence interval actually promises, and what a p-value is - together with the three places where each of those is routinely read as something stronger than it is.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Causal Inference

Why a comparison between the treated and the untreated can carry the wrong sign, what randomisation actually buys, and the rule that says which variables to adjust for - including the ones that make the answer worse.

3 modules: 3 modules
Total XP: 320 XP
Mastery gate: 90% to advance

Intermediate

Time Series

What breaks when observations are not independent: a regression that finds a relationship between two series that have nothing to do with each other, standard errors that are wrong by a known factor, and a validation split that reports a model more than five times better than it is.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Information Theory

The one place in this subject where a bound is met exactly: entropy is the shortest any code can be, the best code reaches it, and the surcharge for using the wrong distribution is the loss function you already train with.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Experimentation and A/B Testing

What an online experiment reports when it is too small, watched too often, or read across too many metrics: an effect inflated 2.4 times, a false positive rate of 19% instead of 5%, and a winning segment in almost half of all experiments where nothing happened.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Intermediate

Recommender Systems

Two fitted offsets that deliver two thirds of the accuracy gain before any latent factor is learned, a model 1.28 times worse for the users who have told it least, and the blind spot that opens when a system only ever sees ratings for what it chose to show.

3 modules: 3 modules
Total XP: 330 XP
Mastery gate: 90% to advance

Intermediate

Anomaly Detection

A detector that never fires scores 99.5% accuracy, a ROC of 0.9468 hides an alert queue that is 64% false, distance from the mean scores below chance when the anomalies sit at the centre, and twenty anomalies that group together hide each other from the method built to find them.

3 modules: 3 modules
Total XP: 330 XP
Mastery gate: 90% to advance

Advanced

Language Models and Generative AI

How text becomes numbers, how attention lets a token gather context from the whole sequence, and what pretraining then fine-tuning actually do to the weights.

3 modules: 3 modules
Total XP: 440 XP
Mastery gate: 90% to advance

Advanced

Reinforcement Learning

Acting well when outcomes are uncertain: the Bellman equation and how to solve it, then what changes when the environment is unknown and the agent has to learn from experience alone.

3 modules: 3 modules
Total XP: 440 XP
Mastery gate: 90% to advance

Advanced

Probabilistic Reasoning over Time

Track a world that changes while you watch it through a noisy sensor: the two assumptions that make it tractable, the forward and backward recursions that answer every query about the past and present, and the separate algorithm needed for the most likely history.

4 modules: 4 modules
Total XP: 460 XP
Mastery gate: 90% to advance

Advanced

Decisions Under Partial Observability

An agent that cannot see which state it is in has to act on a distribution instead. That distribution is itself always observable, which turns the problem back into an MDP - over a continuous space, on which the exact algorithms do not close.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance

Advanced

Statistical Learning Theory

Why fitting a sample tells you anything about the world it was drawn from, what the capacity of a model class really measures, and the theorem that says no method is best everywhere - together with what that theorem does not say.

3 modules: 3 modules
Total XP: 340 XP
Mastery gate: 90% to advance