| Unit name | Advanced Deep Learning and Computer Vision |
|---|---|
| Unit code | MATHM0055 |
| Credit points | 20 |
| Level of study | M/7 |
| Teaching block(s) |
Teaching Block 2 (weeks 13 - 24) |
| Unit director | Dr. Song Liu |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
None |
| Units you must take alongside this one (co-requisite units) |
None |
| Units you may not take alongside this one |
None |
| School/department | School of Mathematics |
| Faculty | Faculty of Science and Engineering |
Why is this unit important?
The recent development of deep learning has revolutionised the way we perform artificial intelligence tasks, especially in computer vision. This unit explores influential ideas that enabled many paradigm-shifting applications in computer vision, including those for image classification, generative modelling, and representation learning. These will prepare you to apply state-of-the-art deep learning techniques in your subsequent research or practical projects.
How does this unit fit into your programme of study
Advanced deep learning and computer vision builds on your foundational understanding of neural networks taught in Foundations of AI. You will further explore modern statistical machine learning ideas and methodologies used in computer vision tasks, with a focus on their mathematical and computational underpinnings. These advanced concepts will prepare you not only for your MSc projects during the summer but also for your career as an AI specialist, engineer or researcher.
An overview of content
Throughout the unit there is a focus on theoretical and computational principles in advanced topics including supervised learning tasks in computer vision, representation learning, and generative modelling. You will learn about supervised learning in computer vision (e.g., image classification, object detection, segmentation and captioning) , specialised neural network architectures, representation learning, and generative models for images and other domains.
How will students, personally, be different as a result of the unit
Upon completing this unit, you will be able to confidently evaluate, design and deploy advanced AI approaches to solve problems in computer vision (e.g., image or video classification or generation) and other domains requiring advanced knowledge of deep learning architectures.
Learning outcomes
On successful completion of this unit, you will be able to explain mathematical and computational principles that underpin modern deep learning tasks. Specifically, you will be able to:
You will learn through a range of synchronous and asynchronous activities including lectures and problem classes/computer laboratories. Problem classes/computer laboratories will be used to provide direct feedback on linked exercises.
Tasks which help you learn and prepare you for summative tasks (formative):
The lecture notes will provide questions and worked answers. Additionally, some of the practical lab sheets will provide exercises and worked answers. Feedback on these questions and exercises will be provided by a combination of laboratory/problem classes and Q&A sessions.
Tasks which count towards your unit mark (summative):
Assessment Structure:
Coursework (30%), assessing ILOs 2 and 4. The coursework consists of individual programming assignments focusing on solving CV problems using public datasets. In the assignments, you are expected to implement and fine-tune CV algorithms for specific tasks, and to report your results using appropriate performance metrics.
In-person Exam (70%) assessing ILOs 1 and 3. This is a closed-book individual exam assessing your mastery of the theoretical and conceptual basis of deep learning and computer vision.
When assessment does not go to plan:
When required by the Board of Examiners, you will normally complete reassessments in the same formats as those outlined above. However, the Board may modify the form or number of reassessments required. Details of reassessments are normally confirmed by the School shortly after the notification of your results at the end of the academic year.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. MATHM0055).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The assessment methods listed in this unit specification are designed to enable students to demonstrate the named learning outcomes (LOs). Where a disability prevents a student from undertaking a specific method of assessment, schools will make reasonable adjustments to support a student to demonstrate the LO by an alternative method or with additional resources.
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
