Undergraduate Course: Machine Learning Theory (INFR11202)
Course Outline
School | School of Informatics |
College | College of Science and Engineering |
Credit level (Normal year taken) | SCQF Level 11 (Year 4 Undergraduate) |
Availability | Available to all students |
SCQF Credits | 10 |
ECTS Credits | 5 |
Summary | This course is an introduction to the theory of learning algorithms and their properties that are relevant to the widespread use of machine learning. The course will contain two types of topics. (i) Fundamental properties of learning - such as accuracy, complexity, stability, and confidence of learning models - that are important in robust, reliable autonomous systems (e.g. IoT, autonomous vehicles etc). (ii) Aspects of learning that are of social relevance. These include Privacy (protection of sensitive information) and fairness (no bias against individuals or groups). With the increasing popularity of ML, these socially relevant aspects of learning are considered critical in its widespread use, and they are the focus of significant research and development.
The course aims to provide a firm foundation in measuring these qualities carefully, and in interpreting and analysing their implications and tradeoffs.
|
Course description |
The following is an indicative list of topics to be covered in the course:
1. Characterising accuracy and confidence of learning models. E.g. probably approximately correct (PAC) guarantees
2. Complexity of learning models (e.g. VC dimension) and bias-complexity tradeoff
3. Importance of low complexity models (Occam's razor): Structural risk minimisation, regularisation
4. Robustness. E.g. stability, smoothness and Lipschitz properties
5. Kernel methods
6. Statistical notions of Privacy in learning. E.g. Differential privacy.
7. Statistical/mathematical approach to Fairness. Individual and group fairness, and relation to privacy and other learning properties.
The topics will be discussed with reference to standard machine learning techniques, and examples of realistic problems. Our approach will include precise definitions and analysis as well as examples and intuitive explanations. The relevance and domain of applicability of the various concepts will be discussed.
Tutorials and problem sets will be available to help understanding and exploration of the subject.
|
Information for Visiting Students
Pre-requisites | Same as "other requirements" |
High Demand Course? |
Yes |
Course Delivery Information
|
Academic year 2022/23, Available to all students (SV1)
|
Quota: None |
Course Start |
Semester 2 |
Timetable |
Timetable |
Learning and Teaching activities (Further Info) |
Total Hours:
100
(
Lecture Hours 18,
Seminar/Tutorial Hours 3,
Feedback/Feedforward Hours 1,
Summative Assessment Hours 2,
Revision Session Hours 1,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
73 )
|
Assessment (Further Info) |
Written Exam
70 %,
Coursework
30 %,
Practical Exam
0 %
|
Additional Information (Assessment) |
Written Exam 70%
Coursework 30%
Practical Exam 0% |
Feedback |
Students will receive feedback in the forms of assessment of coursework, tutorials, and problem sets. |
Exam Information |
Exam Diet |
Paper Name |
Hours & Minutes |
|
Main Exam Diet S2 (April/May) | | 2:00 | |
Learning Outcomes
On completion of this course, the student will be able to:
- Interpret and explain rigorous statements about properties of machine learning methods.
- Evaluate properties of learning models through proofs and examples.
- Relate, compare, and contrast the implications of various qualities of machine learning models covered in the course.
- Formulate precise mathematical requirements corresponding to desired properties in real learning problems, and explain their decisions.
|
Reading List
Book: 'Understanding Machine Learning: From Theory to Algorithms', by Shai Ben-David and Shai Shalev-Schwartz. |
Additional Information
Graduate Attributes and Skills |
Problem solving, critical/analytical thinking, independent learning, written communication. |
Special Arrangements |
Students should be confident in standard machine learning ideas: training and test sets, classification, regression, clustering; standard machine learning methods: support vector machines, linear regression, k-means etc. Good understanding of probability and probabilistic arguments is necessary.
Experience of hands on data analysis and use of machine learning can be beneficial, but is not necessary.
|
Keywords | Machine Learning,Data Science,Algorithms,Theory |
Contacts
Course organiser | Dr Rik Sarkar
Tel: (0131 6)50 4444
Email: |
Course secretary | Miss Lori Anderson
Tel: (0131 6)51 4164
Email: |
|
|