UNIT 018 h allocated
Neural learning
- Dense neural networks
- activations
- loss functions
- backpropagation
← Course catalogue
DEEP LEARNING & PERCEPTION / CORE
DL301Deep learning: DNNs, PyTorch, CNNs & sequences
32 h productive allocation12 h 48 m learning + 19 h 12 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.
Core studio / CPU-friendly local or notebook environment
WHAT YOU SHOULD BE ABLE TO DEMONSTRATE
- Explain the assumptions and failure modes in neural learning.
- Complete the practical: train a small CPU-friendly dense network and one transfer-learning or sequence baseline, then diagnose overfitting using held-out curves.
- Defend the resulting training script with reproducible evidence.
THE SUBJECTS / FOUR CONNECTED UNITS
What you will study.
UNIT 028 h allocated
PyTorch training systems
- Tensors and autograd
- dataloaders
- training and evaluation modes
- checkpointing
UNIT 038 h allocated
Spatial representations
- Convolutions
- pooling
- transfer learning
- augmentation and leakage
UNIT 048 h allocated
Temporal representations
- RNN and LSTM
- sequence windows
- chronological validation
- learning curves
THE TRAINING STUDIO
Make the subject
visible in your work.
Train a small CPU-friendly dense network and one transfer-learning or sequence baseline, then diagnose overfitting using held-out curves.
Evidence to produce
- Training script
- loss curves
- checkpoint manifest
- comparison with simpler baseline
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.
How do architecture, optimisation algorithm and library differ?
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.