Redirecting to another URL

A newly awarded £3.5M EPSRC Programme Grant EP/V026259/1 Maths4DL on the Mathematics of Deep Learning, joint between Bath, Cambridge and UCL, which started in February 2022.

Newsletter 1: November 2022

Newsletter 1

Workshop on Deep Learning for Environmental Problems

University of Bath, in the Wolfson Room

This workshop took place on 20-21st September 2022.

More information, and the schedule, can be found at workshop details

Speakers:

Andrew McRae (Oxford), Cyril Morcrette (Met Office), Amulya Chevuturi (UK Centre for Ecology and Hydrology),Olga Isupova (Bath), Hui Tang (Bath), Ivan Sudakow (Open University), Peter Deuben (ECMWF)

Overview

Machine learning, in particular Deep Learning (DL) based on ‘neural networks’, is one of the fastest growing areas of modern science and technology, which has potentially an enormous and transformative impact on all areas of our lives. The applications of DL embrace many disciplines such as biomedical sciences, computer vision, the physical sciences, the social sciences, speech recognition, gaming, music and finance. However, alongside this explosive growth has been a concern about the lack of understanding behind DL and the way that DL based algorithms make their decisions. This leads to a lack of trustworthiness in the use of some of these algorithms. A reason for this is that the huge successes of Deep Learning are not all well understood, the results are sometimes mysterious, and there is often a lack of a clear link between the data training DL algorithms, and the decisions made by those algorithms. This Programme Grant aims to put DL onto a firm mathematical grounding, and will combine theory, modelling, data and computation to help unlock the next generation of deep learning.

The research work in the grant will comprise an interlocked set of work packages aimed to address both the theoretical development of DL (so that it becomes explainable) and the algorithmic development (so that it becomes trustworthy). These will then be linked to the development of DL in a number of key application areas, linked to and supported by industry, including medical image processing, partial differential equations and environmental problems.

Investigators

Simon Arridge (UCL)
Chris Budd OBE (Bath)
Matthias Ehrhardt (Bath)
Bangti Jin (UCL)
Richard Nickl (Cambridge)
Carola-Bibiane Schönlieb (Cambridge)

Post Doctoral Researchers

Teo Deveney (Bath)
Kweku Abraham (Cambridge)
Rob Tovey (UCL)

Domain Experts

Tatiana Bubba (Bath)
Yury Korolev (Cambridge)
Lisa Kreusser (Bath)

Programme Manager

Helena Lake (Bath)

Opening Workshop

To mark the start of the grant a two day hybrid opening workshop was held on 21st-22nd April.

Speakers:

Kweku Abraham (Cambridge), Francis Bach (INRIA), Keith Briggs (BT), Teo Deveney (Bath), Margaret Duff (Bath), Lisa Kreusser (Bath), Yuri Kurylov (Cambridge), Gitta Kutyniok (LMU, Munich), Weinan E (Princeton), Timo Schirmer (GE Healthcare), Kwinten van Weverberg (Met Office), Jong Chul Ye (KAIST).

The speakers presentations can be found on the workshop website: Opening workshop