Bath Engineering & Design Studentships: Knowledge Representation in Bio-Inspired Neural Networks

An alternative start date may be possible if agreed with your intended supervisors and the Doctoral College.

Project Background:

Artificial Intelligence (AI) currently dominates most modern computing tasks, predominantly through their scaled-up versions deep neural networks (DNNs). Despite the constant improvement in efficiency, the data and power demands of AI are ever growing due to their very fast-paced development.

This project focuses on bio-inspired knowledge representation in AI models. For example, we may want to replace an existing face profile in a facial recognition system with a different face profile without retraining the entire model. To do this efficiently, one needs to identify the specific parts of that model representing the information of interest. This challenge is closely related to abstraction and concept learning, which are central to human generalization but remain less explicit and interpretable in most machine learning models [1].

The project will look at models such as spiking neural networks (SNNs) and consider the problems of knowledge representation and localised model editing. SNNs have been considered the third generation of ANNs which, besides being more biologically realistic, are characterised by data sparsity and power efficiency [2]. The ability of today’s hardware to emulate biological neurons is constantly improving [3]. Being able to characterise the representation of knowledge in such networks has a strong impact on efficient AI as well as enabling better hypotheses for knowledge representation in the brain. The project is expected to lead to publications in top AI and Computational Neuroscience conferences and journals.

Candidate requirements:

Applicants must have, or be about to obtain, a UK Honours degree 1st or 2.1, or international equivalent, in a discipline directly relevant to the PhD. A master’s level qualification would also be advantageous.

Non-UK applicants, who are not currently studying in the UK, must meet the programme’s English language requirement before the application deadline – no exceptions will be considered.

Informal enquiries are encouraged. Direct these to Dr Dorian Florescu.

Please follow the below instructions carefully.

You must make a formal application via the University of Bath’s online application form for a PhD in Electronic and Electrical Engineering.

Please note that you can apply for a maximum of two PhD projects on this programme.

In the ‘Funding Your Studies’ section, you must select ‘University of Bath URSA’ from one of the drop-down menus.

In the ‘Your PhD project’ section, you must quote the project title in the PhD project title field, and you must quote the lead supervisor’s name in the field ‘Name of intended supervisor at University of Bath.’

If you are applying for two projects, you must quote the project title for your second choice project in the field ‘Project 2 Title’ and the lead supervisor’s name in ‘Name of intended supervisor for 2nd choice project at University of Bath.

You must ensure that you follow the above steps correctly. Failure to complete these steps will cause errors in the automated processing of your application and may mean that you are not considered for a particular project.

Equality, Diversity and Inclusion

We value a diverse research environment and strive to be an inclusive university, where difference is celebrated and respected. We encourage applications from under-represented groups.

If you have circumstances that you feel we should be aware of that have affected your educational attainment, then please feel free to tell us about it in your application form. The best way to do this is a short paragraph at the end of your personal statement.

The Disability Service ensures that individuals with disabilities are provided the support that they need. If you state if your application that you have a disability, the Disability Service will contact you as part of this process to discuss your needs.

Keywords

AI, Bio-inspired, Model editing, Spiking Neural Network

Funding Notes

Applicants will be considered for a studentship. The Faculty of Engineering and Design at the University of Bath has studentships available for Home and Overseas students. However, in line with UKRI policy, the number of studentships available to Overseas students are capped. Studentships cover tuition fees, provide a £1k per annum training support fee, and a maintenance stipend (£21,805 2026/27 rate). International students will be required to cover the cost of a Student visa and Immigration Health Surcharge from personal funds.

References

1. Ilievski, F., Hammer, B., Van Harmelen, F., Paassen, B., Saralajew, S., Schmid, U., ... & Villmann, T. (2025). Aligning generalization between humans and machines. Nature Machine Intelligence, 7(9), 1378-1389.
2. Li, G., Deng, L., Tang, H., Pan, G., Tian, Y., Roy, K., & Maass, W. (2024). Brain-inspired computing: A systematic survey and future trends. Proceedings of the IEEE.
3. Fu, S., Gao, H., Wang, S., Wang, X., Woodard, T., Wang, Z., ... & Yao, J. (2025). Constructing artificial neurons with functional parameters comprehensively matching biological values. Nature Communications, 16(1), 8599.