Information geometry of machine learning and its applications
Eligibility: UK/International (including EU) graduates with the required entry requirements
Funding details: Bursary plus tuition fees (UK/International - including EU at international rates from September 2021)
Duration: Full-Time – between three and three and a half years fixed term
Application deadline: 20 May 2021
Interview date: Will be confirmed to shortlisted candidates
Start date: September 2021
For further details contact: Professor Eun-jin Kim
This fully-funded PhD project is part of the Cotutelle arrangement between Coventry University, UK and Deakin University, Melbourne, Australia.
The successful applicant will spend the first year at Coventry University, the following year at Deakin University, and the final 1.5 years at Coventry University.
An ever growing number of high-quality big data from nature and laboratories has revealed the ubiquity of non-equlibrium behavior which is random and unpredictable with significant temporal variabilities. Their behaviour cannot be predicted accurately but requires a probabilistic approach. Furthermore, since information processing is shared among different complex dynamics, information theoretical method can be particularly useful.
Recent years have witnessed the increased awareness of information as a useful physical concept, e.g. in resolving the famous Maxwell’s demon paradox (extracting work from information), or in setting various thermodynamic inequality/uncertainty relations. In particular, an information-geometric theory is a powerful method to understand and classify time-varying processes and data. The key idea is that the very nature of time-varying evolution enables us to utilise “geometry" to describe the evolution by quantifying how the “information" unfolds in time through information geometry. The latter refers to the application of the techniques of differential geometry in probability, statistics and data science by using differential geometry to define the metric (a notion of length).
In our project, our aim will be to investigate the role of information geometry in machine learning and develop new analytical/computational and machine-learning techniques of information geometry, with a view to apply to complex “big data” datasets to uncover the complexity of the links between the parts of dynamical systems generating the time-series data.
This is a fully-funded studentship, including:
- Full tuition fees (for up to 4 years)
- A stipend for up to 3.5 years (£15,000/$AUD 28,092 per year) subject to satisfactory progress
- A one-time economy return airfare to host institution
- Student visa and medical insurance for the period at host partner
- Conference allowances
Throughout the programme, the candidates will have a joint supervisory team and work in close collaboration with researchers in both UK and Australia. The supervisory team offers a substantial track record in successful doctoral supervision and expertise in the thematic areas identified.
The successful candidate will receive comprehensive research training including technical, personal and professional skills.
All researchers at Coventry University (from PhD to Professor) are part of the Doctoral College and Centre for Research Capability and Development, which provides support with high-quality training and career development activities.
Applicants must meet the admission and scholarship criteria for both Coventry University and Deakin University for entry to the cotutelle programme.
- Applicants should have graduated within the top 15% of their undergraduate cohort. This might include a high 2:1 in a relevant discipline/subject area with a minimum 70% mark (80% for Australian graduates) in the project element or equivalent with a minimum 70% overall module average (80% for Australian graduates).
- A Masters degree in a relevant subject area, with overall mark at minimum Merit level. In addition, the mark for the Masters dissertation (or equivalent) must be a minimum of 80%. Please note that where a candidate has 70-79% and can provide evidence of research experience to meet equivalency to the minimum first-class honours equivalent (80%+) additional evidence can be submitted and may include independently peer-reviewed publications, research-related awards or prizes and/or professional reports.
- Language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component).
- The potential to engage in innovative research and to complete the PhD within a prescribed period of study.
For an overview of each University’s entry requirements please visit:
Please note that it is essential to be able to physically locate to both Coventry University (England) and Deakin University (Australia).
How to apply
To find out more about the project, please contact Professor Eun-jin Kim.
All applications require full supporting documentation, a covering letter, plus a 2000-word supporting statement showing how the applicant’s expertise and interests are relevant to the project.
Please note that applications must be made to both universities.
What is the application process?
Applications are submitted to both institutions. Applicants must ensure they meet eligibility requirements. Selection involves academic staff from both institutions. Shortlisted applicants will be interviewed by a panel including academic staff from each institution. Applicants will need to submit copies of certificates to both institutions in line with their respective requirements.