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.
A18 Neural-network mathematics
Advanced pathA: Advanced appliedplannedabout 180 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
Derives backpropagation and separates empirical behaviour from guarantees.
Prerequisites
- Required
- A09 Mathematics of statistical learning, B06 Multivariable & vector calculus, B19 Numerical linear algebra
- Recommended
- none
- Can be taken at the same time
- none
- Everything required, transitively (23 courses)
- A02, A09, B01, B02, B03, B04, B05, B06, B08, B09, B11, B12, B13, B15, B17, B19, B20, F01, F02, F03, G01, G03, U09
- Courses that require this one
- E36
Concept-level units
Units follow the syllabus order, as a recommended sequence rather than a gate.
- Computational graphs
- Backpropagation
- Initialization and gradients
- Optimization behaviour
- Approximation themes
- Reliable numerical experiments
Assessable outcome
Derive backpropagation and distinguish empirical behaviour from mathematical guarantees.
Assessment design
- deeper problem sets
- reconstruction of an unfamiliar argument
- advanced source reading
- cumulative examination or substantial project
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.
- Prince · Understanding Deep Learning
- Goodfellow et al
Content record
- Version
- 0.0.0
- Review
- no review of any kind
- Provenance
- catalogue imported from the owner brief of 29 Oct 2026; no teaching content authored
- Known issues
- none recorded
- Type
- course
Bridges and laboratories
- Laboratory: Computational graphs and backpropagation planned Expose derivatives and numerical checks, not only animations
You and this course
Reading your plan on this device…