Postgraduate Course: MIGS: Computational Methods for Data Driven Modelling (MATH11220)
Course Outline
| School | School of Mathematics |
College | College of Science and Engineering |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Not available to visiting students |
| SCQF Credits | 15 |
ECTS Credits | 7.5 |
| Summary | Topics covered will include-
- Optimisation
- Bayesian inference
- Sampling methods
- Uncertainty qualification
The course uses an intuitive hands-on approach with Python as a platform and will include case studies from industrial partners. |
| Course description |
Mainly in the first two semesters, opportunities to attend generic skills training will be made available to you and you are encouraged to make the most of this. It may also be possible to arrange specific training to meet a demand if several students are interested in a specific area.
Semester 1
The SMSTC Symposium in Perth includes workshops on tutoring, marking and how to get a PhD.
Computer Tools & Skills I & II micro project report, and write summary of talk in MAC-MIGS Colloquium.
Presentation skills
Semester 2
Maths Modelling Camp.
Short presentation at MAC-MIGS Residential Symposium.
All Year
Gain experience of writing LaTeX in SMSTC assignments. Store in Training Log.
We expect students to attend general mathematical activities such as seminars, discussions, colloquia and EMS meetings where possible, provided they do not clash with taught courses and other 1st Year MAC-MIGS programme activities.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Course Delivery Information
|
| Academic year 2021/22, Not available to visiting students (SS1)
|
Quota: None |
| Course Start |
Semester 1 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
150
(
Lecture Hours 20,
Programme Level Learning and Teaching Hours 3,
Directed Learning and Independent Learning Hours
127 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
100% coursework |
| Feedback |
Not entered |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Understand the differences and the similarities between traditional deterministic regularization methods and their Bayesian counterparts for inverse problems.
- Be able to solve computationally (non smooth and smooth) convex optimisation problems using Python
- Understand basic concepts about Bayesian inference
- Be able to sample from high dimensional probability distributions using Python
- Familiarise themselves with machine learning approaches for solving inverse problems
|
Additional Information
| Graduate Attributes and Skills |
Not entered |
| Special Arrangements |
This course is only open to students on CDT programmes in the Maxwell Institute Graduate School. |
| Keywords | MIGS;CDT |
Contacts
| Course organiser | Dr Benjamin Goddard
Tel: (0131 6)50 5127
Email: B.Goddard@ed.ac.uk |
Course secretary | Mrs Katy Cameron
Tel: (0131 6)50 5085
Email: Katy.Cameron@ed.ac.uk |
|
|
University Homepage