Artificial Intelligence
From what a neuron is to modern large language models — the ideas, the maths, and the systems behind them.
In this track · 10 lessons
Foundations
3 lessons- 1What is a neuron?~12 minInteractiveEvery neural network, up to the largest language model, is built from one tiny computation repeated billions of times. This is that computation — from scratch.
- 2From neurons to networks~12 minInteractiveOne neuron draws a straight line. Stack them into layers and a network can represent almost any pattern. Here is how single neurons become a network.
- 3How a network learns~14 minInteractiveNobody sets a network's weights by hand. It learns them by measuring its error and rolling downhill. Meet the loss function and gradient descent.
Core
3 lessons- 4Backpropagation — learning in deep networks~14 minInteractiveGradient descent needs the slope of the loss for every weight. In a deep network, backpropagation computes all of them in a single backward sweep.
- 5Turning words into vectors~13 minInteractiveNetworks only do arithmetic, so language must become numbers first. Embeddings turn words into vectors where direction encodes meaning.
- 6Attention and transformers~15 minInteractiveAttention lets each word gather meaning from the words around it. Stack it and you get the transformer — the architecture behind every modern LLM.
Advanced
2 lessons- 7Training that generalises~14 minInteractiveA model that aces its training data can still fail on everything new. The real goal is generalisation — and the tension between underfitting and overfitting is the heart of it.
- 8Pretraining — predict the next token~13 minInteractiveLarge language models are trained on one deceptively simple task: predict the next token. That single objective, at scale, produces astonishing capability.
Expert
2 lessons- 9From base model to assistant~15 minInteractiveA pretrained model knows language but isn't helpful. Instruction tuning and preference tuning (RLHF) turn a raw next-token predictor into an assistant.
- 10Using LLMs well — limits, context and cost~14 minInteractiveThe expert's edge isn't just knowing how models work — it's knowing what they can't do, and the practical levers that decide whether a system works in production.
Stay in the loop
Get notified as new Artificial Intelligence lessons launch
Bring us the problem, not a perfect specification
Tell us what needs to change, who it affects and any important deadline. We will review the context and reply with useful next questions.
- 01Share contextDescribe the workflow, constraint or risk.
- 02Clarify togetherWe identify missing facts and useful options.
- 03Choose a startAgree a focused assessment or delivery step.