Our Team
Our Interests
The ‘Information, Inference and Machine Learning’ group focuses on the foundations and applications of information theory, information processing, and machine learning systems
Concretely, our current research concentrates on the information-theoreticfoundations of learning paradigms such as supervised learning, unsupervised learning, deep learning and meta-learning.
It also concentrates — in collaboration with domain experts — on applications of machine learning systems to a variety of areas including arts and humanities and climate science.
Our research is funded by diverse bodies such as EPSRC, InnovateUK, H2020, Royal Society and Industry
Publications » Projects »Latest News
-
Martin Ferianc has joined the ‘Information, Inference and Machine Learning’ group in October.
-
Zahra Sabetsarvestani has successfully defended her PhD in September.
Featured Projects
Innovative Machine Learning to Constrain Aerosol-Cloud Climate Impact
This research project – a collaboration between data scientists and climate scientists – will develop machine learning solutions to the analysis of the exploding amounts of climate data in order to deliver breakthroughs in climate research, whilst training the next generation of scientists.
This project is funded by the European Commission.
Francisco de Goya, Doña Isabel de Porcel (NG1473)
Art Through the ICT Lens
This research project develops signal processing, image processing, and machine learning technology ingesting multi-dimensional datasets acquired on paintings to unveil distributions of materials within artwork.
This project is funded by the EPSRC.
Hurbert and Jan van Eyck Ghent Altarpiece
Multi-Modal Signal Processing for Art Investigation
This research project develops machine learning technology ingesting multi-dimensional datasets acquired on paintings to reveal features of interest within paintings such as underdrawings, pentimenti, or concealed designs.
This project is funded by a Royal Society Newton International Fellowship.
Information-Theoretic Foundations of Deep Learning
This research project explores the information-theoretic foundations of deep learning systems, including architectures, algorithms, and generalization bounds for supervised and semi-supervised deep learning approaches.
This project is funded by a Royal Society Newton International Fellowship.
Learning to Communicate
This research project develops physical-layer technology based on deep learning solutions applicable to machine type communications.
This project is funded by the EPSRC.
Learning Privacy for the Internet of Visual Things
This research project develops privacy enhancing technologies for visual data based on deep learning solutions with applications to internet of things systems.
This project is funded by CISCO.