Image Formation and Classical Computer Vision
Camera models, filtering, features, homographies, stereo and optical flow, built in NumPy and SciPy.
Track · Semesters 3–4
Computer Vision & Generative Models
From image formation and classical vision to deep visual recognition, then generative models of images, and vision-language, 3D vision and world models.
Four subjects, in order
Semester 3 · Subject 1 of 4 Semester 3 · Subject 2 of 4 Deep Visual Recognition
CNNs and Vision Transformers, detection and segmentation, self-supervised learning and compression for a CPU.
Semester 4 · Subject 3 of 4 Deep Generative Models
Autoregressive models, VAEs, flows, GANs, diffusion and flow matching, each derived and built from scratch.
Semester 4 · Subject 4 of 4 Vision-Language, 3D Vision and World Models
Image-text models, 3D reconstruction, radiance fields and world models, trained small on one CPU core.
Then, your capstone
Your capstone is a solo project in this track, in five graded milestones.
Capstone Project
A solo project in your track, in five graded milestones from proposal to report, demo and viva.
Before you start the track
The track builds on the whole core: every Semester 1 and 2 subject.
- Linear Algebra & Calculus for ML
- Probability & Statistics for ML
- Foundations of Machine Learning
- Classical AI: Search, Logic & Reasoning
- Data Engineering & Databases for ML
- Neural Networks & Deep Learning
- Optimisation & Training at Scale
- Sequence Models & Transformers
- Responsible AI, Ethics & Governance
Required for Image Formation and Classical Computer Vision
Linear Algebra & Calculus for ML
Neural Networks & Deep Learning
Electives
Open to both tracks.
Probabilistic ML & Bayesian Methods
Posteriors exact and approximate: Gaussian processes, variational inference, MCMC and calibrated uncertainty.
Reinforcement Learning Foundations
Bandits, temporal-difference learning, Q-learning, deep Q-networks and policy gradients, on environments you write.
The other track
Prefer Language Models & LLM Engineering? See the Language models track