Fundamental Components of Deep Learning: A category-theoretic approach

Date(s)
Wednesday 20th September 2023 (10:00-11:00)
Contact
Event Convenor Contact: A.M.Kasprzyk@nottingham.ac.uk
Description
Speaker's Name: Bruno Gavranović
Speaker's Affiliation: Strathclyde
Speaker's Research Theme(s): Symbolic computational mathematics,Computational statistics and machine learning
Abstract:
Deep learning, despite its remarkable achievements, is still a young field. Like the early stages of many scientific disciplines, it is permeated by ad-hoc design decisions. From the intricacies of the implementation of backpropagation, through new and poorly understood phenomena such as double descent, scaling laws or in-context learning, to a growing zoo of neural network architectures - there are few unifying principles in deep learning, and no uniform and compositional mathematical foundation. In this talk I'll present a novel perspective on deep learning by utilising the mathematical framework of category theory. I'll identify two main conceptual components of neural networks, report on progress made throughout last years by the research community in formalising them, and show how they've been used to describe backpropagation, architectures, and supervised learning in general, shedding a new light on the existing field.

Venue: Zoom
Online Conference Link: https://us06web.zoom.us/j/84644928641?pwd=Vm5UNy8xdnk0WnhBeVlSSXVlK2Y5UT09

School of Mathematical Sciences

The University of Nottingham
University Park
Nottingham, NG7 2RD

For all enquiries please visit:
www.nottingham.ac.uk/enquire