Sustainable Human Like Adaptation: Auto Adaptive Machine Learning for Evolving Real World Systems

Summary

SPEAR Research Programme: Fully Funded PhD Opportunities

The Semiconductor and Photonics Education and Research (SPEAR) Centre, funded by PEACEPLUS and managed by the Special EU Programmes Body (SEUPB), is a cross-border project that will provide Ulster University and ATU with access to an all-island network of research groups and industry partners. The project receives strategic support from Tyndall and advisory support from Seagate Technology. The SPEAR Centre is a photonics research, training, and innovation response to the challenges outlined in the EU Chips Act 2023, while also addressing existing deficits in high skill/high-value employment and research infrastructure in the border region.

A key element of the project is a doctoral training initiative comprising of 15 PhD students, delivered in collaboration with ATU, Tyndall National Institute, and Seagate Technology, a global leader in data storage and photonics innovation. Three PhD students will be based at Ulster University (Derry~Londonderry campus) and will join a collaborative Doctoral College alongside PhD students at ATU (Letterkenny campus) and Tyndall National Institute. This initiative involves co-supervised research, joint training activities, summer schools, industry engagement, and access to advanced infrastructure. The following PhD studentship is now open for recruitment to the SPEAR Doctoral College.

This PhD project focuses on developing the next generation of sustainable, self adapting machine learning (ML) systems capable of operating reliably in real world environments that change continuously over time. Many systems in engineering, healthcare, and the life sciences evolve in ways that violate the stationarity assumptions underpinning traditional machine learning (ML) models, causing their performance to deteriorate in the field. Existing continual learning approaches often attempt to compensate through frequent or continuous retraining; however, this can be computationally expensive, energy intensive, and prone to catastrophic forgetting.

Building on our previous work, which showed that covariate shift detection using an Exponentially Weighted Moving Average (EWMA) can trigger highly efficient, need based model updates, this PhD will develop an advanced auto adaptive ML framework. The framework will integrate state of the art change point detection (CPD) with modern continual learning strategies to identify when meaningful changes occur and retrain only when necessary. This targeted adaptation aims to ensure long term robustness while minimising computational and environmental costs.

A key feature of the project is the development of real time digital twins—virtual counterparts of physical systems that mirror their behaviour as conditions evolve. These twins will support early detection of performance degradation, safer system adaptation, and autonomous self-maintenance.

The framework will be applied and evaluated in two high impact domains:

* Brain–computer interfaces (BCIs) to enable long term, home operable assistive and rehabilitation technologies for people with neurological or neuromuscular impairments.
* Predictive maintenance in smart manufacturing, particularly in photonic device fabrication.

This project offers an exciting opportunity to contribute to sustainable AI, human centred neurotechnology, and intelligent self maintaining industrial systems with significant societal and technological impact. The successful candidate will benefit from Ulster’s wide-ranging expertise in Neurotechnology and Machine Learning and access to cutting-edge neuroimaging facilities and high performance computing, and will interact with leading international collaborators.

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.

• Experience using research methods or other approaches relevant to the subject domain
• 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
• Use of personal initiative as evidenced by record of work above that normally expected at career stage.

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:

• SEUPB Peace Plus (SPEAR)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £20,516 per annum for three years (subject to satisfactory academic performance).

• Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
• Republic of Ireland (ROI) nationals are eligible to receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
• Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
• 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.