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 cheap GPGPU compute coupled with large datasets and some neat algorithms. This module will look at how deep learning works, from theoretical foundations right through to practical implementation.
Linked modules
Prerequisites: COMP3206 or COMP3223 or COMP6229 or COMP6245
Aims and Objectives
Learning Outcomes
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- The key factors that have made deep learning successful for various applications
- Underlying mathematical and algorithmic principles of deep learning
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Critically appraise the merits and shortcomings of model architectures on specific problems
- Critical appraisal of recent scientific literature in deep learning
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 working with deep learning libraries in order to create and evaluate network architectures
Syllabus
Historical Developments
- Deep Belief Networks
- CNNs, LeNet and the ImageNet competition
- RNNs
Learning Algorithms
- Initialisation
- SGD, Momentum, etc.
Deep Belief Networks
- RBMs
Auto-encoders
- variational
- denoising
CNNs
- Architectures
- Region Propositions
- Semantic Segmentation
Sequence Modelling
- Linear Embeddings
- RNNs
∗ LSTMs
∗ GRUs
∗ back-prop through time
Deep Learning Technologies
Applications
- Computer Vision
- Natural Language Processing & Generation
- Speech
Learning and Teaching
Teaching and learning methods
Lectures, labs and guided self-study
| Type | Hours |
|---|---|
| Specialist Laboratory | 20 |
| Lecture | 24 |
| Wider reading or practice | 46 |
| Completion of assessment task | 60 |
| Total study time | 150 |
Resources & Reading list
Textbooks
Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016). Deep Learning.
Assessment
Summative
Summative assessment description
| Method | Percentage contribution |
|---|---|
| Continuous Assessment | 100% |
Referral
Referral assessment description
| Method | Percentage contribution |
|---|---|
| Set Task | 100% |
Repeat
Repeat assessment description
| Method | Percentage contribution |
|---|---|
| Set Task | 100% |
Repeat Information
Repeat type: Internal & External