NeuroAI Pathway to Explainable AI (XAI)

Summary

AI Shortcomings

While the application of AI has progressed significantly, current AI algorithms do not provide insight into how computations are performed. This lack of explainable AI (XAI) severely limits its application in areas such as finance and healthcare, and furthermore XAI has been largely overlooked in AI research. Therefore, there is a pressing need to focus research on making AI based computations understandable to a broad audience [1].

Solution

A new research area called NeuroAI could potentially deliver XAI [2] as this area bridges the knowledge gap between experimental neuroscience and AI [2]. Experimental neuroscience focuses on understanding brain function and this knowledge could steer the development of new AI by creating NeuroAI models that provide biological clarity on how real biological neurons and glia cells compute [3].

Project Description and Impact

The objective of this project is to investigate if networks with different cell types (glia and neuron cells) and cell diversity could advance AI computing and point to a new generation of XAI. The PhD candidate will gain experience in:

1. Working with experimental neuroscientists and analysing their data outputs.
2. Developing new advanced biologically based computational models that underpin interactions between different cell types in the brain.
3. Developing NeuroAI models that capture these interactions at network level.
4. Evaluate NeuroAI models using metrics such as accuracy, explainability, training duration and complexity.
5. Dissemination of research finding at national and international event.

PhD Candidate Profile

The ideal PhD candidate will hold a strong undergraduate or master's degree in computational neuroscience, computer science, mathematics, biology, or related fields. The candidate will be based within the Computational Neuroscience & Neuromorphic Engineering (CNET) research team at Ulster University and will work with academics and PhD students on the translation of neuroscience outputs to NeuroAI algorithms.

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%
• For VCRS Awards, Masters at 75%
• 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:

• Department for the Economy (DfE)
• Vice Chancellor's Research Scholarship (VCRS)

Our fully funded PhD scholarships will cover tuition fees and provide a maintenance allowance of £19,237 (tbc) per annum for three years* (subject to satisfactory academic performance).  A Research Training Support Grant (RTSG) of £900 per annum is also available.

These scholarships, funded via the Department for the Economy (DfE) and the Vice Chancellor’s Research Scholarships (VCRS), are open to applicants worldwide, regardless of residency or domicile.

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.

*Part time PhD scholarships may be available, based on 0.5 of the full time rate, and will require a six year registration period (individual project advertisements will note where part time options apply).

Due consideration should be given to financing your studies.