• University of Cambridge Featured PhD Programmes
  • Aberdeen University Featured PhD Programmes
  • University of Pennsylvania Featured PhD Programmes
  • FindA University Ltd Featured PhD Programmes
  • Staffordshire University Featured PhD Programmes
  • University of Tasmania Featured PhD Programmes
University of Liverpool Featured PhD Programmes
Imperial College London Featured PhD Programmes
EPSRC Featured PhD Programmes
University College London Featured PhD Programmes
FindA University Ltd Featured PhD Programmes

Conformal Predictors in Machine Learning

This project is no longer listed in the FindAPhD
database and may not be available.

Click here to search the FindAPhD database
for PhD studentship opportunities
  • Full or part time
    Prof Gammerman
  • Application Deadline
    No more applications being accepted
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

Applications are invited for a PhD studentship in the field of Machine Learning at Royal Holloway, University of London. This is a fully-funded EPSRC iCASE award with support from Thales UK as the industry partner.

We are an elite Computer Science department with world-class experts in Machine Learning and several other fields. Research in Machine Learning and Pattern Recognition research is developed in the Computer Learning Research Centre (CLRC) - details are available at http://clrc.rhul.ac.uk. The students enjoy a very lively research culture and are fully involved in various activities of the Department.

The project will involve research into a novel machine learning technique in developing conformal predictors (CPs) when additional or privileged information is available. It is known that privileged information techniques developed by V.Vapnik make it possible to achieve better accuracy when applying support vector machines (SVM+). The PhD study will consider problems of anomaly detection, cluster analysis and other problems in the framework of conformal predictors when some privileged information can substantially improve the quality and reliability of prediction. The student will investigate theoretical underpinning of the method with experimental verification using real or synthetic data from appropriate scenarios and sources. A study also includes a generalisation of conformal predictors, beyond i.i.d. (independent and identically distributed) assumption, referred to as the online compression model (OCM), and how the privileged information would influence the results of predictions.

The essential requirements for a suitable applicant are: a first or upper second class honours degree in Computer Science or a related discipline; excellent mathematical and analytical skills; the ability to engage fully with the industrial partner; and meet English language requirements. Among desirable skills are some experience in data analysis and a background in the Physical Sciences.

Starting date: as soon as possible but before 31 March 2016.

Interested candidates may contact Professor Gammerman informally before submitting their application. Applications must be made on-line to Royal Holloway, University of London https://www.royalholloway.ac.uk/studyhere/researchdegrees/applying/home.aspx and must include a cover letter, curriculum vitae and the names and contact details of three referees.

Funding Notes

This is a fully-funded EPSRC iCASE award with support from Thales UK as the industry partner. The studentship covers PhD fees for UK/EU students and includes a stipend of circa £16,000 per annum for 3.5 years (exact value to be confirmed).

As this is an iCASE studentship, the student will be expected to spend up to three months working at Thales in Crawley. In accordance with company policies candidates must comply with Baseline Personnel Security Standard requirements and so will be asked to provide evidence of identity and eligibility.

Related Subjects

How good is research at Royal Holloway, University of London in Computer Science and Informatics?

FTE Category A staff submitted: 24.45

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

Click here to see the results for all UK universities
Share this page:

Cookie Policy    X