Bayes Centre

Explainable Machine Learning: A Practical Introduction

This online credit-bearing course is aimed at aspiring data scientists and software engineers, who have technical backgrounds and roles in organisations involving or related to machine learning and artificial intelligence.

Course Summary

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: 

Explainable Machine Learning: A Practical Introduction

Course Delivery Information

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. 

Entry Requirements

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.

Course Fees and Funding

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.

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:

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.

 

Apply Now

Applications for November 2021 are now closed.

In order to verify that you meet the entry requirements for this course, you will be required to provide either:

  • a degree certificate/transcript for your highest/most relevant academic qualification, or
  • a CV and reference from an employer (if employed) or professional associate (if unemployed) outlining your suitability for the course

The degree certificate/transcript or CV should be emailed to bayes-training@ed.ac.uk within 24 hours of submitting your application. References should be emailed to the same address (from an institutional/company account if from your employer) within 1 week of submitting your application. 

Once complete, your application will be processed in 1-2 weeks. Applications will be processed on a first come, first served basis with priority given to applicants who meet the criteria for a funded place. We aim to email all applicants within 2 weeks of submission regardless of the outcome of their application.