New INI Programme: Mathematics of deep learning

Written by Josh Stevens
March 2, 2020

We’re pleased to announce that the Isaac Newton Institute (INI) has approved the Mathematics of deep learning programme, co-organised by CCIMI director Carola-Bibiane Schönlieb and CCIMI faculty member Anders Hansen. The programme will take place at the INI from 1st July to 17th December 2021.

Due to the massive amounts of training data complemented by a tremendously increased computing power, deep neural networks have recently seen an impressive comeback. In fact, we currently witness how algorithms based on deep neural networks are infusing numerous aspects of the public sector such as being used for pre-screening job applications or revolutionizing the healthcare industry. A similarly strong impact can be observed on science itself. Deep learning based approaches have proven very useful within certain mathematical problem settings such as solving ill-posed inverse problems or high-dimensional partial differential equations, sometimes already leading to state-of-the-art algorithms. However, most of the related research is still empirically driven and a sound theoretical foundation is largely missing. This is not only a significant problem from a scientific viewpoint, but particularly critical for sensitive applications such as in the health care sector. Thus there exists a tremendous need for mathematics of deep learning.

Peter Bartlett (University of California, Berkeley)
Anders Hansen (University of Cambridge)
Arnulf Jentzen (ETH Zürich)
Gitta Kutyniok (Technische Universität Berlin)
Carola-Bibiane Schönlieb (University of Cambridge)

More information about the programme is available on the Isaac Newton Website here.