Under construction. This area is a framework being built: most courses have no teaching material yet, and things may change or break. Private self-study. Not an official programme and not recognised by any ministry or school. No qualification, mark or document is issued, and “years 1 to 3” and “advanced” are names of study paths only.
E38 Probabilistic generative models
Advanced pathE: Proposed extensionsplannedabout 120 h (planning estimate)
Planned: syllabus only, no teaching material yet. Nothing on this page can be studied; it describes what the course would cover.
Named in: Advanced applied mathematics pathway
Why this course
Covers the models behind modern image and text generation.
Prerequisites
- Required
- A08 Bayesian inference & statistical decisions, E37 Modern deep-learning architectures, A07 Stochastic calculus & modelling
- Recommended
- none
- Can be taken at the same time
- none
- Everything required, transitively (22 courses)
- A07, A08, B01, B02, B03, B04, B05, B06, B08, B09, B11, B13, B15, B17, B20, E37, F01, F02, G01, G03, U07, U14
- Courses that require this one
- none
Concept-level units
Units follow the syllabus order, as a recommended sequence rather than a gate.
- Latent-variable models and the evidence lower bound
- Variational autoencoders
- Normalizing flows and change of variables
- Generative adversarial networks and divergences
- Score matching and diffusion models
- Autoregressive models and likelihood
- Evaluation of generative models
- Memorization, privacy and misuse
Assessable outcome
Derive the training objective of a VAE and of a diffusion model, and say what each assumes.
Assessment design
- topic exercises
- mixed problem sets
- unseen proof or derivation problems
- cumulative examination
cumulative; uses spaced retrieval
Resources
Every title here is candidate, unverified unless marked verified. Titles were suggested while planning. Nobody has checked that they exist, what they cost or how they are licensed.
- Kingma and Welling · Auto-encoding variational Bayes (paper)
- Ho, Jain, Abbeel · Denoising diffusion probabilistic models (paper)
- Murphy · Probabilistic Machine Learning: Advanced Topics (free)
Content record
- Version
- 0.0.0
- Review
- no review of any kind
- Provenance
- PROPOSED by the assistant on 4 Nov 2026 so that a person with a mathematics degree can read AI articles fluently; not in the owner's brief; APPROVED by the owner on 4 Nov 2026 as an elective; still needs a curriculum reviewer
- Known issues
- Approved as an elective on 4 Nov 2026; syllabus only, no lessons, candidate resources unverified, needs a curriculum reviewer.
- Type
- course
Bridges and laboratories
No bridge or laboratory is attached to this course yet.
You and this course
Reading your plan on this device…