Part of the Phi-ML meets Engineering seminar series, this bi-monthly event 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.
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. Seminar speakers describe rigorous computational speedups over established digital algorithms as well as application to large scale machine learning training through thermodynamic natural gradient descent. Seminar speakers also present experimental results confirming the theoretical framework of thermodynamic computing. Finally, the series explore connections to uncertainty quantification and machine learning through open-source library posteriors.
Subscribe to the mailing list to attend, details here.
External event: The University of Aberdeen is a member of The Turing University Network, a network committed to offering UK universities the opportunity to engage and collaborate both with The Alan Turing Institute and its broader networks in academia, industry and the public sector. Discover more about the university becoming a member of The Turing University Network: Turing Universities Network | Research | The University of Aberdeen (abdn.ac.uk).