The University of Bath is inviting applications for the following PhD project in the Department of Computer Science commencing in October 2023.
The successful student will be part of the Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) which performs world-leading multi-disciplinary research in Intelligent Visual and Interactive Technology. Funded by the EPSRC and the University of Bath, CAMERA exists to accelerate the impact of fundamental research being undertaken at the University in the Departments of Computer Science, Health and Psychology. The successful candidate will work closely work with the experts from CAMERA and potentially with collaborators from the University of Bristol and project partners associated with the MyWorld programme.
Overview of the Research:
Deep generative models have been applied across a wide variety of domains including image, shape, text and speech synthesis tasks, and are showing promise for molecule design in material science and drug discovery. Common approaches have included flow-based (Normalizing Flows), latent variable (VAEs) and implicit generative (GANs) models.
More recently, Denoising diffusion models (DDMs) have emerged as a new powerful class of probabilistic generative models. Inspired by non-equilibrium thermodynamics, a forward diffusion perturbs some input data towards random noise while a deep model is tasked with learning to reverse the process. As a result, can be used to generate desired data samples starting from random noise.
Remarkably, this simple idea has led to state-of-the-art performance on a range of downstream tasks, most famously text-to-image generation via the likes of DALLE-2, Imagen and Stable Diffusion models.
However, despite these great successes in generating high-quality image samples, there remain significant limitations. For example, a crucial drawback of DDMs is their reliance on the learned inverse being described in terms of an ordinary or a stochastic differential equation (ODE or SDE, respectively) which is typically difficult to solve leading to expensive sample generation.
What are you going to do?
Research on diffusion models is still in its early stages with significant potential and thus we seek a PhD candidate that will contribute to theoretical improvements in this field.
The flexibility in the core formulation provides a rich seam of possibilities for exploring generalizations that retain the robustness of this framework while formulating models which are more adaptable and efficient. For instance, it has recently been shown that DDMS are not strongly dependent on the choice of image degradation, which has opened the possibility for an entire family of generative models can be constructed by varying this choice.
Other key research directions include efficient sampling and improved likelihood, as well as deriving new formulations in which the latent space is interpretable, the ability to interface with other types of generative models and handle data structures beyond images.
Project keywords: Machine Learning, Diffusion models, Data Structures, Computer Vision.
Candidate Requirements:
Applicants should hold, or expect to receive, a First Class or good Upper Second Class Honours degree (or the equivalent). A master’s level qualification would also be advantageous.
Applicants without a Masters level course in computer vision, computer graphics, machine learning, applied mathematics, physics, or a strongly correlated field, would have to provide strong justification (and evidence) that they would be able to handle the maths and programming necessary to complete a PhD in this field.
Programming experience is a particular advantage, specifically proficiency in numerical Python / C++ or similar. All of the techniques we use build on Linear Algebra and it would be desirable for the candidate to have experience in applied mathematics / numerical methods.
Non-UK applicants must meet our English language entry requirement.
Enquiries and Applications:
Informal enquiries are welcomed and should be directed to the lead supervisor, Prof Neill Campbell, on email address [Email Address Removed].
Formal applications should be made via the University of Bath’s online application form for a PhD in Computer Science.
More information about applying for a PhD at Bath may be found on our website.
NOTE: Applications may close earlier than the advertised deadline if a suitable candidate is found. We therefore recommend that you contact the lead supervisor prior to applying and submit your formal application as early as possible.
Funding Eligibility:
To be eligible for funding, you must qualify as a Home student. The eligibility criteria for Home fee status are detailed and too complex to be summarised here in full; however, as a general guide, the following applicants will normally qualify subject to meeting residency requirements: UK nationals (living in the UK or EEA/Switzerland), Irish nationals (living in the UK or EEA/Switzerland), those with Indefinite Leave to Remain and EU nationals with pre-settled or settled status in the UK under the EU Settlement Scheme). This is not intended to be an exhaustive list. Additional information may be found on our fee status guidance webpage, on the GOV.UK website and on the UKCISA website.
Equality, Diversity and Inclusion:
We value a diverse research environment and aim to be an inclusive university, where difference is celebrated and respected. We welcome and 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.