Tom Diethe: Research Fellow, SPHERE

BIO

Signal Processing · Computational Statistics · Machine Learning

Tom Diethe was born in London, UK, in 1977. He received a B.Sc. in Experimental Psychology from the University of Bristol in 2000, then taking up an industrial research position at QinetiQ, where in 2004 he received the Future Systems Technology division “Star Award” for outstanding achievement. In 2005 he received an M.Sc. with distinction and best project award in Intelligent Systems, and then in 2010 received a Ph.D. in machine learning applied to multivariate signal processing, both from University College London. After two post-doctoral positions in the departments of Computer Science and Statistical Science at UCL, he has since worked for the British Medical Journal and Microsoft Research Cambridge, before taking up a position as a Research Fellow for the SPHERE IRC at the Department of Electrical Engineering of the University of Bristol. His current research interests include probabilistic machine learning, computational statistics, learning theory, and data fusion.

Qualifications:

BSc Hons. Experimental Psychology, University of Bristol
MSc (Distinction). Intelligent Systems, University College London
PhD. Machine Learning applied to multivariate signal processing, University College London

Former positions:

Researcher, Machine Learning and Perception Group, Microsoft Research Cambridge
Machine Learning Consultant, British Medical Journal Group, London
PDRA, Department of Statistical Science, University College London
PDRA, Department of Computer Science, University College London
Senior Software Engineer, Centre for Human Sciences, QinetiQ

Awards:

11/2006: Award for best project for the MSc Intelligent Systems 2005-2006
02/2004: QinetiQ Future Systems Technology (FST) division “Star Award” for outstanding achievement

Academic.

Academic Interests: Computational Statistics & Machine Learning · Learning Theory · Kernel Methods · Convex Optimisation · Sparsity · Multiple Kernel Learning · Online Learning · Active Learning · Transfer Learning · Bayesian Inference · Graphical Models · Approximate Inference · Signal Processing · Compressed Sensing · Analysis of Brain Signals (EEG, MEG, fMRI)

My page on videolectures.net


Academic duties

Referee for Journals: Journal of Machine Learning Research · Machine Learning Journal · Neural Networks · Psychological Review · Pattern Analysis and Applications · Neural Computing and Applications · IEEE Transactions on Neural Networks and Learning Systems · IEEE Signal Processing · IEEE Transactions on Pattern Analysis and Machine Intelligence · Transactions on Image Processing · EURASIP Journal on Advances in Signal Processing · Signal Image and Video Processing · Pattern Recognition Letters.

Referee for Conferences Neural Information Processing Systems (NIPS) · Artificial Intelligence and Statistics (AISTATS) · European Conference of Machine Learning (ECML-PKDD) · Knowledge Discovery in Databases (KDD) · International Conference on Neural Information Processing (ICONIP)

Consulting.

Contact Tom for: consulting offers; new ventures; expertise requests.


About me.

My Erdos Number is 3, by virtue of having co-authored papers with John Shawe-Taylor, and my Morphy Number is 6, by virtue of having played a blitz game against Jon Speelman (I've also played several games against Raymond Keene, who probably has a M.N. of 5 too).

Getting in touch.

I get many enquiries from undergraduate students from overseas institutions requesting placements at this University for research internships under my supervision. The University of Bristol does not run a research internship programme. Please do not contact me about internships.