Generative models with diffusion

The powerful engines behind synthetic data generation in AI are diffusion models, aka, stochastic differential equations. A success story that draws a lot of public attention recently is the generation of high-resolution images from text prompts, e.g. stable diffusion and DALLE-2, which have achieved amazing results.

The objective of this project is twofold. First, we aim to explore the application of diffusion models to generation of other data types, e.g. network data. One use case of this extension is drug discovery. Second, we aim to analyse the mathematical properties of diffusion models for various data structures.

You should have a background in Probability and Statistics. It would be advantageous to have experience in Programming (language agnostic). You should be a highly motivated individual and possess a strong sense of curiosity. The ability to study independently, think critically and collaborate with others is essential.

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. The UK Government is also offering Doctoral Student Loans for eligible 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%.