Imperial College London Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
The University of Manchester Featured PhD Programmes
Cardiff University Featured PhD Programmes

PhD in Computing Science: Data compression at the quantum limit for big-data machine learning applications

Project Description


The University of Glasgow (UofG) is home to world-leading research in the fields of imaging and computing science and home to the UK Hub for Quantum Imaging Technologies, QuantIC ( who are co-funding this PhD research project in collaboration with a high-tech startup company, Dotphoton (

You will be part of a unique, world-leading and international research team, with training in cutting edge research techniques involving computational techniques, AI and data compression applied to next generation biological and quantum images.

The Project

We are searching for a highly motivated student to work at the interface between computing science (machine learning and artificial neural networks) and imaging (classical and quantum imaging) in collaboration with a high-tech start-up company.

The aim of this project is to bring together expertise developed within Dotphoton, based in Switzerland, with machine learning and artificial neural networks developed at UofG for imaging applications under study within QuantIC, the UK Hub for quantum imaging based at UofG. One of the main obstacles in applying machine learning to image data is the huge amount of memory required, in particular RAM during the learning process. This is currently proving to be a bottle-neck for the development and deployment of artificial neural networks applied to high pixel density images. As an example, the two UofG supervisors have recently developed an ANN that can decode the random speckle patterns at the output from a multimode fibre and estimate the input, unscrambled image. The technique is very promising yet is currently limited to images sizes of 90x90 pixels.

The main goal is to use/develop Dotphoton’s approach to data compression and thus fit up to four times more image data in a GPU memory. We will search for options in which we can either decode on-the-fly, or format the data such that it can efficiently be directly used by the machine learning algorithm. This will be a game-changer for machine learning applied to imaging in all sectors, e.g. lidar, MRI, bio-imaging but also more in general, in any applications where large amounts of data are involved.

Applications will be considered on a rolling basis. For enquires specific to the project, please email or .

Funding Notes

Funding is available to cover tuition fees UK applicants for 3.5 years, as well as paying a stipend at the Research Council rate (estimated £14,999 for Session 2019-20).

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.