• University of Glasgow Featured PhD Programmes
  • University of Bristol Featured PhD Programmes
  • University of Manchester Featured PhD Programmes
  • University of Southampton Featured PhD Programmes
  • University of Surrey Featured PhD Programmes
  • Queen’s University Belfast Featured PhD Programmes
  • University of Stirling Featured PhD Programmes
  • Northumbria University Featured PhD Programmes
University of Bristol Featured PhD Programmes
Aston University Featured PhD Programmes
Imperial College London Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of Reading Featured PhD Programmes

Fulfilling humans’ ‘right-to-explanation’ by integrating machine learning, natural language generation and information visualization

This project is no longer listed in the FindAPhD
database and may not be available.

Click here to search the FindAPhD database
for PhD studentship opportunities
  • Full or part time
    Dr Y Sripada
    Dr W Pang
    Prof G M Coghill
  • Application Deadline
    Applications accepted all year round
  • Self-Funded PhD Students Only
    Self-Funded PhD Students Only

Project Description

Advances in machine learning (ML) are transforming our society. As more and more machine learnt models become work colleagues to humans (loan applications are, for example, processed by algorithms mainly and humans are called in for help occasionally), humans expect improved access to models, particularly to their inner workings. New regulatory regimes all over the world are introducing humans’ ‘right-to-explanation’. This means, for example, a customer whose loan application has been turned down could ask for explanation. Evidently, new research is required to investigate computational techniques for explaining to humans the inner workings of machine learnt models. This project aims to bring together techniques from natural language generation (NLG), machine learning (ML) and information visualization (InfoVis).

Given a training dataset a multitude of ML techniques exist to learn several different models, each model differing from the other along a number of important dimensions such as predictive power and explanatory power. While predictive power is the primary property guiding model development explanatory power is the desirable property to ensure human comprehension of the models.

In this PhD project you will work with a variety of machine learnt models with different amounts of predictive and explanatory power. Your aim would be to develop computational techniques to explain models and their application on test data to humans. This involves studying machine learnt models for their transparency and explanatory power and at the same time studying humans to understand the properties of ‘good explanations’.

You will then run experiments with human participants to evaluate the explanations auto-generated by your algorithms.

The successful candidate should have, or expect to have, an Honours Degree at 2.1 or above (or equivalent) in Computing Science and other related disciplines.

Knowledge of: Essential: machine learning basics; programming in Java, Python or R.
Desirable: natural language generation; artificial intelligence;

Funding Notes

There is no funding available for this project, it is for self-funded students only


This project is advertised in relation to the research areas of the discipline of Computing Science. Formal applications can be completed online: http://www.abdn.ac.uk/postgraduate/apply. You should apply for PhD in Computing Science, to ensure that your application is passed to the correct College for processing. NOTE CLEARLY THE NAME OF THE SUPERVISOR and EXACT PROJECT TITLE ON THE APPLICATION FORM. Applicants are limited to applying for a maximum of 2 projects. Any further applications received will be automatically withdrawn.

Informal inquiries can be made to Dr Y Sripada ([email protected]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Graduate School Admissions Unit ([email protected]).

Cookie Policy    X