Explainable and Interpretable AI (XAI)

Apply and key information  

This project is funded by:

    • DfE CDP Award in collaboration with Thales IAS

Summary

This PhD project, a collaboration between Ulster University and Thales IAS, aims to advance research in Explainable AI (XAI), addressing the growing need for trust and transparency in AI systems. While Deep Neural Networks (DNNs) have driven significant advancements in autonomous systems with improved accuracy, scalability, and generalisation, understanding and explaining how AI models generate specific results remains a major challenge.

XAI comprises methods and processes that help users comprehend and trust machine learning outputs. It is critical for implementing responsible AI, enabling fairness, accountability, and explainability at scale. Various XAI methods exist, applicable across different stages of the machine learning pipeline, but their selection and application for specific use cases need further investigation.

This PhD project will:
* Provide a taxonomy of XAI methods to serve as a reference for this expanding field.
* Explore AI/ML models (focused on image classification and regression techniques) and associated datasets to identify where XAI can be effectively applied.
* Compare XAI methods to select those that meet specific use-case requirements.
* Define example requirements for XAI in the context of a selected use-case.
* Develop and train an AI/ML model incorporating XAI components and verify its compliance with the specified requirements.

The successful applicant will collaborate closely with Thales IAS, and have the opportunity to spend three months on-site (subject to passing security requirements) to access resources, consult with experts, and gain hands-on experience in data analysis focused on research and development tasks aligned with the research project or related challenges of interest to Thales.

We particularly welcome applicants with a strong background in computer science, artificial intelligence, or a closely related discipline. Candidates should have robust programming skills and demonstrable experience in computational methods. While a Master’s degree in a relevant field is beneficial, applicants must also hold an undergraduate degree (at the level listed in the Essential Criteria) in a cognate discipline such as computer science, software engineering, AI, mathematics, or a related technical field.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

  • A demonstrable interest in the research area associated with the studentship

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

  • First Class Honours (1st) Degree
  • Masters at 70%
  • Experience using research methods or other approaches relevant to the subject domain
  • Work experience relevant to the proposed project
  • Publications - peer-reviewed
  • Experience of presentation of research findings

Equal Opportunities

The University is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.

Appointment will be made on merit.

Funding and eligibility

This project is funded by:

  • DfE CDP Award in collaboration with Thales IAS

This PhD opportunity is funded by the Collaborative Doctoral Partnership (CDP) Studentship Awards 2025. The standard PhD stipend of £20,780 per annum is enhanced by an additional top-up of £30,000 over the three-year duration of the studentship (£10,000 per year). This results in a generous, tax-free stipend of £30,000 per year (equivalent to £2,500 per month) for the PhD researcher. The studentship also covers three years of tuition fees (worth over £14,000) and provides extensive support for research training and project running costs.

To be eligible for this scholarships, applicants must meet the following criteria:

  • Be a UK National, or
  • Have settled status, or
  • Have pre-settled status, or
  • Have indefinite leave to remain or enter, or
  • be an Irish National

Applicants should also meet the residency criteria which requires that they have lived in the EEA, Switzerland, the UK or Gibraltar for at least the three years preceding the start date of the research degree programme.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies.

Recommended reading

What is Explainable AI? Software Engineering Institute’s Insights, Carnegie Mellon University, Accessed November 12, 2024
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI. Information Fusion, Vol. 58, pp. 82-115

The Doctoral College at Ulster University

Key dates

Submission deadline
Friday 16 May 2025
03:00PM

Interview Date
9th June 2025

Preferred student start date
15 September 2025

Applying

Apply Online  

Contact supervisor

Professor Michaela Black

Other supervisors