Postgraduate Course: Audio Machine Learning (PG) (MUSI11078)
Course Outline
| School | Edinburgh College of Art |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | Machine Learning is a subfield of Artificial Intelligence which uses algorithms that learn from data. In this course you will learn about the fundamental ideas, mathematics and methods underpinning state-of-the-art machine learning techniques. You will also gain hands-on experience working with data and applying Machine Learning techniques using the Python programming language. The course is based around applying machine learning methods to problems in audio and music, and the specific considerations arising when working with audio data. |
| Course description |
In this course you will explore a number of modern machine learning methods and gain hands-on experience implementing and applying algorithms to real-world data, using the Python programming language. The course will cover topics including:
- Review of Linear Algebra and Calculus
- Feature Engineering for Audio
- Classification and Regression tasks
- Neural Networks
The course specifically focusses on music and audio problems (not including speech), such as audio effects processing, music information retrieval, sound classification or music/instrument synthesis.
The course content will be delivered by weekly 2-hour class sessions which will start by giving a broad overview of the key ideas and domains of machine learning, and move onto more advanced topics, such as neural networks, as the course progresses. Additionally, there will be weekly 2-hour workshop sessions where students will work through practical programming-based exercises based on the weekly class content. Students will be assessed on one practical coding assignment, as well as a project report based on the findings of a group machine learning project, where they will apply material from the lectures to work with real-world data to achieve a range of audio-specific tasks.
During the second half of the course, postgraduate students will prepare and give a 15-minute (non-assessed) 'paper-talk' presentation to the class based on a research paper. Students will be given a list of research papers to choose from and will be responsible for independently researching the topic and preparing a presentation.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Information for Visiting Students
| Pre-requisites | This course requires students to have numeracy competence at a level equivalent to Advanced Higher Maths. |
| High Demand Course? |
Yes |
Course Delivery Information
|
| Academic year 2024/25, Available to all students (SV1)
|
Quota: 15 |
| Course Start |
Semester 2 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 22,
Supervised Practical/Workshop/Studio Hours 22,
Feedback/Feedforward Hours 3,
Summative Assessment Hours 1,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
148 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
This course has 2 assessment components.
- Machine Learning Challenge, 50%, weeks 7-8
- Machine Learning Project Report, 50%, May exam diet
The Machine Learning Challenge consists of programming-based machine learning problems. You will submit Python code along with inline comments clearly explaining what the code is doing. This assignment addresses Learning Outcomes 1, 2 and 3.
The Machine Learning Project Report involves documenting the process and results of group project work in which students attempt to solve a problem using audio-domain data. Students will be responsible for choosing a problem to work on and for choosing a dataset to work with. Groups will present their projects during class toward the end of the semester. The submission comprises an individual report that should include figures, images, and graphs, as well as a description of the main findings of the project. This assignment addresses Learning Outcomes 3, 4 and 5. |
| Feedback |
Formative feedback
Students will receive verbal formative feedback (from both staff and their peers) throughout the course during the workshops, as they work through the tasks provided. Additionally, students will complete a formative programming assignment in the first half of the semester, and feedback based on these submissions will be given to the class. This feedback will feed directly into the Machine Learning Challenge programming assignment.
After the presentations of the group projects, students will receive feedback on their project and presentation from the instructor as well as from their peers. The students will then have time to consider and incorporate this feedback into their final project report.
Summative feedback
Students will receive feedback on the programming-based summative assessment in the form of brief written comments. Additionally, summary feedback will be provided to the whole class in the form of written and verbal notes. Feedback on the project reports will be delivered as written comments. Students will receive individual written feedback and grades on their summative submissions, which will be provided via LEARN VLE as per university regulations.
Postgraduate students will meet with the course organiser prior to their 'paper-talk' presentation that will be given to the class. Verbal feedback will be given on their presentation, allowing students to incorporate and improve their presentations. |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Write clear Python code whose organisation shows awareness of good programming practice
- Implement a range of algorithms used for machine learning
- Apply machine learning techniques to an audio-domain dataset to achieve a defined objective
- Identify, assess and resolve problems arising during the phases of a machine learning project
- Critically evaluate the performance of a machine learning-based solution, considering all relevant criteria
|
Reading List
Books
Jung, Alexander. Machine Learning: The Basics. Springer Nature, 2022.
Available at: https://alexjungaalto.github.io/MLBasicsBook.pdf
Deisenroth, Marc Peter, A. Aldo Faisal, and Cheng Soon Ong. Mathematics for machine learning. Cambridge University Press, 2020.
Available at: https://mml-book.github.io/book/mml-book.pdf
Lee, Wei-Meng. Python Machine Learning / Wei-Meng Lee. Indianapolis, IN: Wiley, 2019. Print.
Raschka, Sebastian, ed. Machine Learning with Pytorch and Scikit-Learn : Develop Machine Learning and Deep Learning Models with Python / Sebastian Raschka [and Three Others], Editor. Birmingham, England ; Packt Publishing, 2022. Print.
Learning Resources
Free Code Camp - Python for Beginners - video, programming course
https://www.youtube.com/watch?v=eWRfhZUzrAc |
Additional Information
| Graduate Attributes and Skills |
Research and Enquiry
Learning about the mathematical basis of machine learning methods will give you a new toolset for understanding and analysing the world around you, allowing you to make connections between the real world and data that can be used to describe it.
Personal and intellectual autonomy
You will gain experience of approaching problems from a machine learning perspective, critically evaluating the trade-offs of various methods, limitations imposed by the available data, and resulting models. This will help you develop the knowledge and skills necessary to critically evaluate machine learning models that are becoming increasingly prevalent in modern life.
Communication
By communicating what you've learned throughout the group project, both as a presentation to your peers and as an assessed written report, you will become more effective at articulating and describing concepts from the field of machine learning. |
| Special Arrangements |
This course requires students to have numeracy competence at a level equivalent to Advanced Higher Maths. |
| Keywords | Music,AI,Coding |
Contacts
| Course organiser | Mr Alec Wright
Tel:
Email: |
Course secretary | Miss Laura Duff
Tel:
Email: |
|
|
University Homepage