Videos
This page brings together selected training resources from the Erlangen Hub, including presentations and contributions from workshops and events.
The Researcher Spotlight series features conversations with Erlangen Hub colleagues, exploring their research, its significance, and their perspectives on what success looks like in their work and for the hub.
This page brings together selected seminars from the Erlangen Hub, featuring invited speakers and research talks. It also contains interviews with our own team and some training videos.
Seminars
Branton DeMoss, University of Oxford
Geometry, Complexity, and Generalization in Learning Systems
In this talk, Branton DeMoss (University of Oxford) will discusses the relationship between compression, complexity, and the geometry of the loss landscape.
Tristan Madeleine, University of Southampton
Learning on graphs: expressivity challenges from graph pooling
Graphs provide a natural framework for relational data across many domains, presenting interesting practical and theoretical challenges for machine learning.
Eng-Jon Ong, QMUL
Estimating Intrinsic Dimensionality with L2N2 This talk introduces L2N2, a simple yet powerful ID estimator based on nearest-neighbour distance ratios that achieves state-of-the-art performance with minimal computational overhead.
Iolo Jones, University of Oxford
Computing Diffusion Geometry
Diffusion geometry is a new theory that reformulates classical calculus and geometry in terms of a diffusion process, allowing these theories to generalise beyond manifolds and be computed from data.
Alessandro Micheli, Imperial
Riemannian Neural Optimal Transport
This talk introduces Riemannian Neural Optimal Transport (RNOT), a continuous neural parameterisation of OT maps that avoids discretisation and incorporates geometric structure directly.
Ambrose Yim, University of Oxford
Geometry of Loops on the Möbius Band
This talk proposes propose a novel representation of a loop’s geometry by representing the distance matrix of the loop as a Morse function on a Möbius band.
Jesse Hoogland
Singular Learning Theory for interpretability
Henrique Ennes
Raphaël Tinarrage
Linear orbits of compact lie groups and machine learning
Xinyu Li
Markov α-potential games: A framework to study multi-agent RL
Michael Bronstein
Geometric deep learning quo vadimus?
Michael Bronstein, Anthea Monod, Jeff Giansiracusa
Erlangen Hub 2025 Conference welcome talk
Thom Badings
How to control your stochastic system? A tale of abstraction and certificates
Edward Pearce-Crump
Around the equivariant world in 45 minutes
Q&As
Q&A with Francesco Fabiano & Thom Badings
This PDRA interview offers a behind-the-scenes insight into how interdisciplinary research is advancing our understanding of decision making across complex real-world contexts.
Q&A with Professor Michael Bronstein
In this Researcher Spotlight Hub Director, and DeepMind Professor of Artificial Intelligence, Michael Bronstein, discusses the idea and vision behind the name of the Erlangen AI Hub.
Q&A with Professor Peter Grindrod
In this Researcher Spotlight Knowledge Exchange Lead and Co-Investigator Professor of Mathematics Peter Grindrod discusses the AI research landscape, and his motivations and vision for the Erlangen AI Hub.
Q&A with Professor Jeffrey Giansiracusa
In this spotlight, Hub Co-Director and Durham Lead Professor Jeffrey Giansiracusa reflects on the journey of the Erlangen Hub so far, its long-term impact, and finally the people, ideas and networks which shape it.
Training resources
Peter Grindrod, University of Oxford
Engaging with commercial and public stakeholders – collaborative research for successful impact
Peter Grindrod, University of Oxford
Professional skills: Networking, strategy, and leadership for Early-Career Researchers
Tom Coates, Imperial College London
Trusted Research: What is it and why is it relevant?