Advanced Methods in Machine Learning (982G5)
Note to prospective students: this content is drawn from our database of current courses and modules. The detail does vary from year to year as our courses are constantly under review and continuously improving, but this information should give you a real flavour of what it is like to study at Sussex.
We’re currently reviewing teaching and assessment of our modules in light of the COVID-19 situation. We’ll publish the latest information as soon as possible.
Advanced Methods in Machine Learning
Module 982G5
Module details for 2024/25.
15 credits
FHEQ Level 7 (Masters)
Module Outline
This module will develop your knowledge and understanding of recent machine learning technologies, how they can be applied to different tasks, their benefits, limitations, and open challenges. Key topics include:
• Deep generative models.
• Neural network architectures and inductive biases.
• Learning paradigms, including supervised, self-supervised and semi-supervised.
• Challenges related to the dataset distribution. These topics will be introduced in the context of common applications and tasks in areas such as computer vision and natural language processing, and you will learn how to develop and critique solutions to real-world problems.
Module learning outcomes
Comprehend and apply the key aspects of a range of recent machine learning techniques.
Work independently to propose and implement appropriate machine learning solutions for a specified problem and dataset, demonstrating critical awareness of potential challenges.
Communicate clearly using text and figures an implemented machine learning solution covering the core concepts, rationale for design decisions and critical evaluation.
Critique an implemented system demonstration a systematic approach to quantitative evaluation.
| Type | Timing | Weighting |
|---|---|---|
| Coursework | 100.00% | |
| Coursework components. Weighted as shown below. | ||
| Report | A1 Week 1 | 100.00% |
Timing
Submission deadlines may vary for different types of assignment/groups of students.
Weighting
Coursework components (if listed) total 100% of the overall coursework weighting value.
| Term | Method | Duration | Week pattern |
|---|---|---|---|
| Autumn Semester | Lecture | 1 hour | 11111111111 |
| Autumn Semester | Seminar | 1 hour | 11111111111 |
| Autumn Semester | Laboratory | 1 hour | 11111111111 |
How to read the week pattern
The numbers indicate the weeks of the term and how many events take place each week.
Please note that the Â鶹´«Ã½ will use all reasonable endeavours to deliver courses and modules in accordance with the descriptions set out here. However, the Â鶹´«Ã½ keeps its courses and modules under review with the aim of enhancing quality. Some changes may therefore be made to the form or content of courses or modules shown as part of the normal process of curriculum management.
The Â鶹´«Ã½ reserves the right to make changes to the contents or methods of delivery of, or to discontinue, merge or combine modules, if such action is reasonably considered necessary by the Â鶹´«Ã½. If there are not sufficient student numbers to make a module viable, the Â鶹´«Ã½ reserves the right to cancel such a module. If the Â鶹´«Ã½ withdraws or discontinues a module, it will use its reasonable endeavours to provide a suitable alternative module.