8 March 2021 - Carola-Bibiane Schönlieb (University of Cambridge) - Structure-preserving deep learning
From Greg McCracken
From Greg McCracken
8 March 2021
Carola-Bibiane Schönlieb (University of Cambridge) - Structure-preserving deep learning
Abstract: Over the past few years, deep learning has risen to the foreground as a topic of massive interest, mainly as a result of successes obtained in solving large-scale image processing tasks. There are multiple challenging mathematical problems involved in applying deep learning: most deep learning methods require the solution of hard optimisation problems, and a good understanding of the tradeoff between computational effort, amount of data and model complexity is required to successfully design a deep learning approach for a given problem. A large amount of progress made in deep learning has been based on heuristic explorations, but there is a growing effort to mathematically understand the structure in existing deep learning methods and to systematically design new deep learning methods to preserve certain types of structure in deep learning. In this talk, we review a number of these directions: some deep neural networks can be understood as discretisations of dynamical systems, neural networks can be designed to have desirable properties such as invertibility or group equivariance, and new algorithmic frameworks based on conformal Hamiltonian systems and Riemannian manifolds to solve the optimisation problems have been proposed. We finish by proposing some open problems and possible directions for future research.
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336, VAT Registration Number GB 592 9507 00, and is acknowledged by the UK authorities as a “Recognised body” which has been granted degree awarding powers.
Any views expressed within media held on this service are those of the contributors, should not be taken as approved or endorsed by the University, and do not necessarily reflect the views of the University in respect of any particular issue.
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2021 and may only be used in accordance with the terms of the licence.