Artificial Intelligence
From what a neuron is to modern large language models — the ideas, the maths, and the systems behind them.
Foundations
3 lessonsWhat is a neuron?
Every neural network, up to the largest language model, is built from one tiny computation repeated billions of times. This is that computation — from scratch.
Start lessonFrom neurons to networks
One 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.
Start lessonHow a network learns
Nobody sets a network's weights by hand. It learns them by measuring its error and rolling downhill. Meet the loss function and gradient descent.
Start lessonCore
3 lessonsBackpropagation — learning in deep networks
Gradient descent needs the slope of the loss for every weight. In a deep network, backpropagation computes all of them in a single backward sweep.
Start lessonTurning words into vectors
Networks only do arithmetic, so language must become numbers first. Embeddings turn words into vectors where direction encodes meaning.
Start lessonAttention and transformers
Attention lets each word gather meaning from the words around it. Stack it and you get the transformer — the architecture behind every modern LLM.
Start lessonAdvanced
2 lessonsTraining that generalises
A 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.
Start lessonPretraining — predict the next token
Large language models are trained on one deceptively simple task: predict the next token. That single objective, at scale, produces astonishing capability.
Start lessonExpert
2 lessonsFrom base model to assistant
A pretrained model knows language but isn't helpful. Instruction tuning and preference tuning (RLHF) turn a raw next-token predictor into an assistant.
Start lessonUsing LLMs well — limits, context and cost
The 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.
Start lessonStay 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.