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.
E41 Trustworthy machine learning
Advanced pathE: Proposed extensionsplannedabout 100 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
Robustness, privacy and fairness are the mathematics behind most AI news.
Prerequisites
- Required
- A09 Mathematics of statistical learning, B17 Mathematical statistics I, E37 Modern deep-learning architectures
- Recommended
- none
- Can be taken at the same time
- none
- Everything required, transitively (24 courses)
- A02, A09, B01, B02, B03, B04, B05, B06, B08, B09, B11, B12, B13, B15, B17, B19, B20, E37, F01, F02, F03, G01, G03, U09
- Courses that require this one
- none
Concept-level units
Units follow the syllabus order, as a recommended sequence rather than a gate.
- Adversarial examples and robustness certification
- Differential privacy
- Fairness definitions and their incompatibilities
- Calibration and uncertainty
- Distribution shift
- Interpretability methods and their limits
- Alignment and reward misspecification
- Auditing and reporting
Assessable outcome
Prove a differential-privacy guarantee and show two fairness criteria cannot hold together in a given case.
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.
- Dwork and Roth · The Algorithmic Foundations of Differential Privacy (free)
- Barocas, Hardt, Narayanan · Fairness and Machine Learning (free)
- Hardt and Recht · Patterns, Predictions, and Actions (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…