DOMAINS
Domains
Eight interdependent fields forming a complete chain from mathematical foundations to production engineering.
Math & Statistics Foundations
Vectors, matrices, probability and gradients — the language of AI
Questions this domain answers
- Why can data be written as a matrix?
- Which direction does the gradient actually point?
- Why can softmax be used as a probability?
Machine Learning
Letting programs infer rules from data instead of being hard-coded
Questions this domain answers
- What separates “memorising” from “learning”?
- Why does a model that aces training fail in production?
- What can unlabelled data still be used for?
Deep Learning
Handing feature engineering over to stacked layers
Questions this domain answers
- What is a single neuron actually computing?
- How does backpropagation carry error backwards?
- Why are deeper networks harder to train?
NLP & Large Language Models
From tokenisation to Transformers to models that can talk
Questions this domain answers
- What exactly does a model see when it reads a word?
- Why does attention beat recurrence?
- Why does next-token prediction yield conversation?
Computer Vision
Turning pixels into objects, scenes and 3D structure
Questions this domain answers
- What does a convolution kernel actually learn?
- How do classification, detection and segmentation differ?
- How does a machine recover 3D from 2D images?
Reinforcement Learning
Learning sequences of decisions from trial, error and delayed reward
Questions this domain answers
- Why does delayed reward make the problem hard?
- How do value functions and policy gradients divide the work?
- Why can RL improve large language models?
Generative AI
From judging what something is to synthesising what it should be
Questions this domain answers
- What distribution is a generative model learning?
- Why is diffusion more stable than a GAN?
- How does a text prompt become an image?
AI Engineering, Safety & Ethics
Turning a working model into a usable, trustworthy, accountable product
Questions this domain answers
- How are large models compressed onto consumer hardware?
- How do you evaluate when there is no answer key?
- Why is prompt injection so hard to eliminate?