Project details
Large foundation models, based on Transformers and auto-regressive self-supervised training on sequences, are an exciting new technology that is currently breaking new ground in most fields of AI. The key idea is that one can train a large neural network on large sequences of data (e.g. text, audio, video) autoregressively, i.e. learning to predict frame t from frames 1,2,…,t-1. When such a model is trained, it can then be used to synthetically generate new data sequences, as well as help with downstream tasks such as object classification, anomaly detection etc. In this project we will investigate the possibility of large foundation models trained on sequences of Electroencephalogram (EEG) signals. These are electromagnetic measurements obtained from human brains while carrying out certain tasks. The project will investigate the feasibility and implications of such a foundational model. We will then explore the interplay between EEG and attention levels during a task with the ultimate goal being the design of optimal, automated interventions during a task to help humans stay concentrated. Such technology could have huge implications for learning in children with neurodevelopmental disorders.
94% of Loughborough’s research impact is rated world-leading or internationally excellent. REF 2021
Supervisors
Primary supervisor: George Vogiatzis
Entry requirements
Our entry requirements are listed using standard UK undergraduate degree classifications i.e. first-class honours, upper second-class honours and lower second-class honours. To learn the equivalent for your country, please choose it from the drop-down below.
Entry requirements for United Kingdom
Students should have at least, or expected to achieve, a 2:1 honours degree (or equivalent international qualification) or equivalent experience in an area related to computer science.
English language requirements
Applicants must meet the minimum English language requirements. Further details are available on the International website.
Applicants must meet the minimum English language requirements. Further details are available on the International website.
Fees and funding
Tuition fees for 2025-26 entry
UK fee
To be confirmed Full-time degree per annum
International fee
£28,600 Full-time degree per annum
Fees for the 2025-26 academic year apply to projects starting in October 2025.
Tuition fees cover the cost of your teaching, assessment and operating University facilities such as the library, IT equipment and other support services. University fees and charges can be paid in advance and there are several methods of payment, including online payments and payment by instalment. Fees are reviewed annually and are likely to increase to take into account inflationary pressures.
How to apply
All applications should be made online. Under programme name, select Computer Science. Please quote the advertised reference number: CO/GV – SF3/2025 in your application.
To avoid delays in processing your application, please ensure that you submit a CV and the minimum supporting documents.
The following selection criteria will be used by academic schools to help them make a decision on your application. Please note that this criteria is used for both funded and self-funded projects.
Please note, applications for this project are considered on an ongoing basis once submitted and the project may be withdrawn prior to the application deadline, if a suitable candidate is chosen for the project.
