Module overview
Deep learning has revolutionised numerous fields in recent years. We've witnessed improvements in everything from computer vision through speech analysis to natural language processing as a result of the advent of massively parallel compute coupled with large datasets. This module explores how deep learning can be applied to real world data by implementing models through combinations of pre-built building blocks.
Linked modules
Pre-requisites: COMP3222 OR COMP6246
Aims and Objectives
Learning Outcomes
Subject Specific Practical Skills
Having successfully completed this module you will be able to:
- Apply existing deep learning models to real datasets
- Gain facility in fine tuning and debugging models at training time
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Characterise what types of model architecture might suit certain types of data
- Understand appropriate measures of loss and performance for different types of data
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- When it is and is not appropriate to use deep learning in practical problems
- The key factors that have made deep learning successful for various applications
Syllabus
- Understanding problems and when to use deep learning
- MLPs, CNNs, RNNs, Transformers
- Training network and gradient descent
- Common Network Architectures
- ResNets, etc
- Data augmentation
- Transfer Learning
- Fine Tuning
- Embeddings
- Sequence Processing
- Classical methods
- Deep learning approaches
- Advanced topics
- multimodal models, recent advances, etc.
- Use cases such as:
- Detecting hate speech in social media (transformers + NLP)
- Designing molecules for use as drugs (graph neural nets)
- Diagnosing diseases from chest X-rays (transfer learning)
Learning and Teaching
Teaching and learning methods
Lectures, labs and guided self-study
Type | Hours |
---|---|
Completion of assessment task | 40 |
Lecture | 24 |
Revision | 10 |
Specialist Laboratory | 15 |
Tutorial | 9 |
Wider reading or practice | 52 |
Total study time | 150 |
Assessment
Summative
This is how we’ll formally assess what you have learned in this module.
Method | Percentage contribution |
---|---|
Lab Report | 20% |
Exam | 50% |
Paper or report | 30% |
Referral
This is how we’ll assess you if you don’t meet the criteria to pass this module.
Method | Percentage contribution |
---|---|
Set Task | 100% |
Repeat
An internal repeat is where you take all of your modules again, including any you passed. An external repeat is where you only re-take the modules you failed.
Method | Percentage contribution |
---|---|
Set Task | 100% |
Repeat Information
Repeat type: Internal & External