Geometric deep learning
Deep learning has had tremendous success in a variety of applications. Nevertheless, many data don’t follow a euclidean underlying structure: for example social networks, sensor networks, types of brain imagining, 3D point structures. Geometric deep learning tries to take advantages of techniques coming from deep neural network models and generalise these to non-euclidean domain, such as working with graphs. The purpose of this project would be to see how to incorporate structural information into deep learning algorithms in an efficient way applied to sensor analysis and/or medical imagining.
This is a self funded project
Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. Recently the UK Government made available the Doctoral Student Loans of up to £25,000 for UK and EU students and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.)