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.
E37 Modern deep-learning architectures
Years 1 to 3 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: Years 1 to 3 pathway
Why this course
Lets a mathematician read any architecture description: convolutions, recurrence, attention.
Prerequisites
- Required
- B06 Multivariable & vector calculus, B08 Linear algebra II: abstract structure, B11 Probability I
- Recommended
- A18 Neural-network mathematics
- Can be taken at the same time
- none
- Everything required, transitively (10 courses)
- B01, B02, B03, B04, B05, B06, B08, B11, F01, F02
- Courses that require this one
- E38, E39, E40, E41, E42
Concept-level units
Units follow the syllabus order, as a recommended sequence rather than a gate.
- Backpropagation and automatic differentiation as the chain rule
- Convolutional networks and translation equivariance
- Recurrent networks, LSTM and vanishing gradients
- Attention and the transformer, layer by layer
- Embeddings and tokenization
- Encoder-decoder, masking, positional encodings
- Residual and normalization layers
- Counting parameters and compute
Assessable outcome
Write out the forward pass, parameter count and cost of a transformer block from its description.
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.
- Zhang et al · Dive into Deep Learning (free)
- Vaswani et al · Attention is all you need (paper)
- Prince · Understanding Deep Learning (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…