Get free PhD updates, every week | SIGN UP NOW Get free PhD updates, every week | SIGN UP NOW

Beyond Bayesian Machine Learning: Self-Learning Networks from Imaging Uncertainties [Self-Funded Students Only]

   Cardiff School of Computer Science & Informatics

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Oktay Karakus  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

About the Project: Deep Learning (DL) algorithms have attracted extensive attention specifically in the last decade in almost all signal processing research areas. The reason behind this extensive interest is that they are capable of learning powerful structures which basically map extremely high dimensional data into an easier form for evaluation. However, even though DL algorithms generally perform better than classical approaches, their mapping process depends on blind assumptions, which do not reflect the real scenarios most of the time whilst causing various model-based (epistemic) uncertainties. At the same time, various imaging modalities accommodate different uncertainties caused by their sensor technology, imaging setup/environment, etc. Combined with the epistemic one caused by DL architectures, aleatoric uncertainty (data-related) also causes important performance degradations in DL-based CI algorithms. 

It has been shown in the literature that a probabilistic Bayesian view on DL approaches for various imaging modalities plays an important role especially for quantifying aleatoric and epistemic uncertainties. This project will take one step further beyond the existing Bayesian ML/DL approaches and develop DL structures for remote sensing and medical imaging modalities that are able to self-learn from the existing uncertainties of the problem setup whilst simultaneously performing the required training operations.

Keywords: Uncertainty Quantification, Bayesian Sampling, Deep Learning, Image Processing, Statistical Inference

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.

Desirable Criteria: Holding either a degree-level (applied-) statistics or (applied-) mathematics is a desirable criterion to conduct research in this project.

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via 

In order to be considered candidates must submit the following information: 

  • Supporting statement 
  • CV 
  • In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
  • Qualification certificates and Transcripts
  • Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
  • References x 2 
  • Proof of English language (if applicable)

For more information, please contact [Email Address Removed]

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.

How good is research at Cardiff University in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs