The discipline beneath the algorithms.
Most people learn AI as a stack of tools. This track teaches the mathematics and reasoning underneath — so when the tools change, your understanding doesn't.
Who it's for
Built for these people.
Engineers and analysts moving into machine learning.
CS graduates who want real depth, not just frameworks.
Self-taught developers who skipped the theory and feel it.
Anyone who wants to read a paper and actually follow it.
What you'll be able to do
By the end.
Build models from first principles, not libraries alone.
Reason about bias, variance, and why a model fails.
Choose the right model for a problem — and defend the choice.
Read and understand modern ML literature.
The Curriculum
From the mathematics to a model you built yourself.
A structured sequence — each module builds on the last, with assessments along the way.
The mathematics you actually need
Linear algebra, calculus, and probability — taught only where they earn their place in machine learning.
Supervised learning
Regression and classification: how models learn from labelled data, and where they break.
Evaluation & validation
Bias–variance, cross-validation, and honest metrics — measuring what a model truly knows.
Neural networks from scratch
Build a network by hand: the forward pass, backpropagation, and the intuition behind both.
Optimisation & training dynamics
Gradient descent, regularisation, and the practical art of getting models to converge.
Capstone
Build, train, and evaluate a model end-to-end — and defend your choices against the rubric.
How you're certified
Earned, not awarded for attendance.
Enrol
Join a cohort or start self-paced, placed at the right level for your background.
Learn
Work through the modules with short assessments at each stage.
Build
Complete the capstone — real work, reviewed against a published rubric.
Certify
Earn a GIAI Certificate tied to what you actually produced.
Admissions
Request your place.
We'll send the full syllabus for this track and the next intake dates.