Explainable Machine Learning: A Practical Introduction
Machine learning provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with significant challenges: how do we understand the decisions suggested by these systems in order that we can trust them? In this course, we study, survey and distil the results and observations from the literature.
The course focuses on understanding and applying XAI techniques and judging their shortcomings. The course aims to focus on methodological thinking and understanding principles for the application of post-hoc explainability.
The course helps them understand and apply innovative and state-of-the-art techniques on explaining machine learning models so as to lead and manage the use of machine learning in their work place. Explainability will likely be a key component for encouraging major organisational changes via the wider deployment of artificial intelligence technologies, and this course will provide strong foundations for navigating and critiquing developments in the area.
Further information can be found in the University's course catalogue:
This course is aimed at people with some prior experience in machine learning and programming in Python and who have prior experience working with or within organisations related to the field of machine learning or artificial intelligence.
This is an introductory/intermediate Masters course (SCQF Level 11). It develops your skills and/or provides a detailed overview of the subject - some foundational knowledge or experience is required. Please see the entry requirements for further details. Masters-level courses are relatively intensive and require independent learning, critical thinking, analysis and reflection.
This standalone course expects users to have some prior experience in machine learning and programming in python, but does not require them to have taken any other course per se. (Prior experience in machine learning implies some knowledge of the underlying concepts for one or more standard prediction/classification models e.g., random forests, training, feature selection, and evaluation. Mathematical knowledge of these concepts is not assumed but it is helpful to be able to read machine learning-related mathematical notation.)
You should be educated to a degree level as this course is catering for those seeking postgraduate academic credit. However, professionals with relevant work experience may also apply even if they do not hold a degree qualification.
Check whether your international qualifications meet our general entry requirements:
English Language Requirements
You must be comfortable studying and learning in English if it is not your first language.
On completion of this course, the student will be able to:
- Analyze: Describe the context of the machine learning application and why explainability would help, but also scrutinise which kind of explainability technique is necessary.
- Design: Define the implementation pipeline for the project: provide a means to clean the data, install and set up one or more post hoc explain ability techniques through a self-chosen set of programming platforms.
- Evaluation: Critically reflect on the results from such techniques and suggest how it helps the problem context.
- Apply: Competently apply a wide range of techniques and tools, also knowing their particular features and drawbacks. Have the foundations to understand new and upcoming methods and techniques.
| Start Date: |
1 November 2021 |
| Course Duration: | 10 weeks (1 Nov - 17 Dec (7 weeks) - then a break over Christmas - 17 Jan - 4 Feb (3 weeks)) |
| Total Hours: | 100 (Lecture Hours 10; Tutorial Hours, including assignments 8; Feedback Hours, including assignments 8; Independent Study Hours 74) |
| Method of Assessment: | Coursework 100% (2 coding assignments and a final coding project) |
| Level: |
This is an intermediate Masters-level course (SCQF Level 11). It develops your skills and/or provides a broad understanding of the subject in some detail - some foundational knowledge is required. Please see the entry requirements for further details. Masters-level courses are relatively intensive and require independent learning, critical thinking, analysis and reflection. Assignment 2 is due 1 week after course ends, and 2-3 weeks will be permitted for the final project which will be due 4 weeks after the course end date. |
Course fees for 21/22 are £960, but funded places are available for people employed, unemployed or furloughed in Scotland who meet Scottish Funding Council elgibility criteria.
Funding
Through the Scottish Funding Council (SFC) Upskilling Fund and National Transition Training Fund, a number of fully-funded places are available at The University of Edinburgh on short, standalone courses from the Data Skills Workforce Development Training portfolio.
Eligibility
Funded places are available to those who meet Scottish Funding Council (SFC) fee waiver criteria. Note that course places are limited and priority will be given to those who meet the criteria for SFC-funded places.
Determining eligibility for a funded place for upskilling takes a number of things into account, including fee status, but also location of employer. SFC provide guidance specifically for upskilling courses:
“Courses/provision is open to all Scottish-domiciled/’home fee’ students, which is consistent with SFC’s policy for core funded student places. Students from the rest of the UK (rUK) are not normally considered eligible for SFC funding. If however a university is working with a Scottish/UK employer which has a physical presence or operating in Scotland, rUK employees of that employer would be eligible.”
Organisations like UKCISA, and the University, provide guidance on how to determine your fee status:
- Information on current fee status regulations for studying in Scotland is available here: https://ukcisa.org.uk/Information--Advice/Fees-and-Money/Scotland-fee-status-for-students-starting-from-August-2021.
- You can check your likely fee status here: https://www.ed.ac.uk/tuition-fees/fee-status/work-out
If your fee status is Scotland Fee Rate, RUK Fee Rate, or EU-EEA Pre/Settled Scotland Fee rate, you may be eligible for a funded upskilling place. To determine this we will look at your fee status, residency information and, where relevant, details of your employer, to confirm whether the employer is based in, or has a significant presence, in Scotland.
Funding eligibility will be assessed at the point of each application for each course; you may be asked to provide further information if you do not meet the general residence conditions. Please email us at bayes-training@ed.ac.uk if you would like to discuss your funding eligibility before applying.
Please note that full-time students (including full-time PhD students) are not eligible for funding.
Funding eligibility criteria for the National Transitition Training Fund in the 2021/22 session is still to be confirmed.
How to Apply
Courses are now being updated for the 2021/22 academic year.
Each course will have a distinct start date which will be updated on the Schedule of Courses webpage and each Course page.
Application links will be available in each individual course webpage, which can be accessed from the Courses summary page. Details about entry requirements and any supporting documentation required can also be found on each page.
You can register your interest by joining our mailing list where courses do not have a live application form for this session.
If you have questions about the application process please contact:
You may find additional information in the FAQ section helpful as well:
Useful Links:
You will receive a certificate of attendance after the final assessment date if you have submitted your coursework.
Applications for November are now closed. Please subscribe to our mailing list to be kept informed about course start dates and new courses.
This course is offered as an option to students on the Data Science, Technology and Innovation programme, an innovative and flexible online programme which aims to educate a new generation of interdisciplinary data scientists, technologists and innovators. You can use credits achieved on this course towards postgraduate study on this programme (MSc, PG Diploma or PG Certificate), subject to approval by the Programme Director.
You may also be able to use credits achieved on this course towards other University of Edinburgh postgraduate programmes, subject to the approval of the relevant Programme Director.
Contact Us
