Understanding neural networks and quantification of their uncertainty via exactly solvable models
This talk is the annual Oxford Maths & Stats Colloquium. There will be a Drinks Reception after the talk in the ground floor social area.
The affinity between statistical physics and machine learning has a long history. Theoretical physics often proceeds in terms of solvable synthetic models; I will describe the related line of work on solvable models of simple feed-forward neural networks. I will then discuss how this approach allows us to analyze uncertainty quantification in neural networks, a topic that gained urgency in the dawn of widely deployed artificial intelligence. I will conclude with what I perceive as important specific open questions in the field.
Date: 5 May 2023, 15:30 (Friday, 2nd week, Trinity 2023)
Venue: 24-29 St Giles', 24-29 St Giles' OX1 3LB
Venue Details: Large Lecture Theatre, Department of Statistics
Speaker: Professor Lenka Lenka Zdeborová (École Polytechnique Fédérale de Lausanne)
Organising department: Department of Statistics
Organisers: Beverley Lane (Department of Statistics, University of Oxford), Professor Simon Myers (University of Oxford)
Organiser contact email address: events@stats.ox.ac.uk
Host: Professor Simon Myers (University of Oxford)
Booking required?: Required
Booking url: https://forms.office.com/e/Nw3qSZtzCs
Booking email: events@stats.ox.ac.uk
Audience: Members of the University only
Editor: Beverley Lane