Introduction
This bi-monthly seminar series explores real-world applications of physics-informed machine learning (Φ-ML) methods to the engineering practice. They cover a wide range of topics, offering a cross-sectional view of the state of the art on Φ-ML research, worldwide.
Participants have the opportunity to hear from leading researchers and learn about the latest developments in this emerging field. These seminars also offer the chance to identify and spark collaboration opportunities.
About the event
Thermodynamic hardware represents a novel computing paradigm where a noise-aware analog device is used as a resource for computation. The time evolution of such analog circuits is well-described by stochastic differential equations and can subsequently utilised for linear algebra primitives. We describe rigorous computational speedups over established digital algorithms as well as application to large scale machine learning training through thermodynamic natural gradient descent. We also present experimental results confirming the theoretical framework of thermodynamic computing. Finally, we explore its connections to uncertainty quantification and machine learning through our open-source library posteriors.
Watch on demand:
Recording will be uploaded after the seminar.
