AI fundamentals

From “what is a model?” to how a chatbot picks its next word — nine hands-on lessons, no maths background needed.

Your learning path: AI fundamentals

4 modules, each building on the last. Create a free account to save your progress and earn XP.

What learning means

How a computer can find patterns in examples instead of following rules.

0/2 done

Learning from examples

Teach a computer to spot spam without writing a single rule.

8 minStart here

Fitting a line

Predict a house price with one straight line, and learn what it means for a model to be wrong.

9 minFree

Getting better, step by step

How models improve by measuring their mistakes — and how they can improve too much.

0/2 done

3 Pro

Gradient descent

How a model finds the bottom of a valley it cannot see, one small step at a time.

10 min Pro lesson

4 Pro

Overfitting

Why a model that aces its homework can still fail the exam.

9 min Pro lesson

Neural networks

Build a neuron by hand, then watch a network of them learn shapes no straight line can.

0/2 done

5 Pro

The artificial neuron

Build the tiny decision-maker that every neural network is made of.

9 min Pro lesson

6 Pro

Training a network

Stack neurons into layers and watch them learn to draw real borders on a map.

12 min Pro lesson

How language models work

From words as points in space to the attention mechanism behind modern chatbots.

0/3 done

7 Pro

Words as vectors

Turn words into lists of numbers, and meaning into distance, using real word vectors.

10 min Pro lesson

8 Pro

Attention

How a real language model, GPT-2, works out which earlier words matter to each word.

14 min Pro lesson

9 Pro

Predicting the next word

Watch a real language model, GPT-2, read text as tokens and write it one token at a time.

12 min Pro lesson