Representation learning from fewer labels

The Surrey Institute for People-Centred AI of University of Surrey is inviting applications for multiple funded PhD studentships to commence from 1 July 2022, or as soon as possible thereafter. The students would be based in the Centre for Vision, Speech, and Signal Processing (CVSSP) at the Stag Hill Campus of the University of Surrey.

Start date
1 July 2022
3 years
Application deadline
Funding information
  • UK or international tuition fees
  • Annual tax-free stipend at standard UKRI rate for 3 years full-time
  • Funding for conference travel.



This PhD project will contribute to the field of representation learning including a set of techniques allowing a system to automatically discover the representations needed for any downstream task from raw data. The successful PhD applicants are expected to advance the field of deep representation learning, propose new algorithms and experimental settings, and draw conclusions in the context of artificial intelligence, machine learning and computer vision.

The students are expected to contribute to unsupervised learning, multi-view representation learning, learning from fewer labels, novel domain adaptation methods, semi, and weakly-supervised learning methods. Students will have opportunities to work in collaboration with leading researchers across the world and to benefit from research internships in leading industrial research labs.

Additional notes

As a PhD student, you will receive state-of-the-art workstation with a development GPU for prototyping. Moreover, you will have access to AI Surrey’s compute cluster and big data infrastructure which includes more than 200 high-performance GPUs and state-of-the-art facility.

Eligibility criteria

Applicants for this studentship must have obtained, or be about to obtain, a first or upper second-class UK honours degree, or the equivalent qualifications gained outside the UK, in a numerate discipline, such as computer science, physics, mathematics etc. The student should have a good understanding of linear algebra, probabilities, calculus etc., with a strong background in computing and Python programming. Moreover, good working experience with deep learning frameworks, such as PyTorch or TensorFlow, and hands-on skill on LaTex is also desirable.

English language requirements 

If English is not your first language you will need to have achieved at least 6.0 in IELTS and no less than 6.0 in any section by the start of the project. Alternative tests may also be acceptable (see

How to apply

Applications should be submitted via the Centre for Vision, Speech and Signal Processing PhD programme page. Please clearly state the studentship title and supervisor on your application.


Application deadline

Contact details

Anjan Dutta

Studentships at Surrey

We have a wide range of studentship opportunities available.