1024ºË¹¤³§

Applications are invited for a 3 year PhD to commence in October 2020 or February 2021.

The PhD will be based in the Faculty of Technology, and will be supervised by Dr I. Kagalidis, Dr A. Paraskelidis and Dr N. Nanos.

Artificial neural networks are widely used to undertake complex image analysis, and carry out tasks such as identifying objects in a noisy environment. Typically Neural Networks will be trained in advance. Performance of the system is hence dependent on the quality and amount of training.

Artificial neural networks require vast quantities of accurately labelled training data, e.g. thousands of images with objects accurately defined. This is a time consuming and costly step. In many situations environmental influences such as perspective, reflections and ambient lighting will affect how the system performs.

This project will investigate ways of allowing Neural Network Systems to apply self-learning post deployment and hence continue to improve performance past the initial training stage. Input from multiple sensors will be explored and how this sensor collaboration can improve the self-learning aspect for asset management applications with multi-sensor coverage.

The work will be undertaken in the 1024ºË¹¤³§, as part of a multi-disciplinary team of Engineers and Computer Scientists keen to explore new avenues for the use of Artificial Neural Networks in everyday life.

Fees and funding

Visit the research subject area page for fees and funding information for this project.

Funding availability: Self-funded PhD students only. 

PhD full-time and part-time courses are eligible for the  (UK and EU students only).