UNIT 016 h allocated
Latent-variable learning
- Latent representations
- reconstruction
- variational objectives
- likelihood limits
← Course catalogue
DEEP LEARNING & PERCEPTION / SPECIALIST
DL340Generative modelling: VAEs, GANs & diffusion
24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief
Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.
BEFORE YOU BEGIN
A clear starting point.
Prerequisites: DL301
Specialist studio; environment and faculty must be confirmed before scheduling
WHAT YOU SHOULD BE ABLE TO DEMONSTRATE
- Explain the assumptions and failure modes in latent-variable learning.
- Complete the practical: compare two small generative approaches or sampling settings using an approved dataset and documented quality criteria.
- Defend the resulting dataset record with reproducible evidence.
THE SUBJECTS / FOUR CONNECTED UNITS
What you will study.
UNIT 026 h allocated
Adversarial models
- Generator and discriminator
- instability
- mode collapse
- evaluation
UNIT 036 h allocated
Diffusion models
- Noise schedules
- denoising
- conditioning
- sampling budgets
UNIT 046 h allocated
Responsible evaluation
- Rights and provenance
- diversity
- memorisation
- task-based utility
THE TRAINING STUDIO
Make the subject
visible in your work.
Compare two small generative approaches or sampling settings using an approved dataset and documented quality criteria.
Evidence to produce
- Dataset record
- generation notebook
- diversity and failure analysis
Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.
ASSESS THE REASONING
A question you
should be able to answer.
Why is an attractive sample not sufficient evidence of useful distribution learning?
Review dimensions
Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.
External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.