by The digiLab Team
Updated 12 February 2024
digiLab Newsletter: Issue 2
Interested in applications of probabilistic ML across fusion and other complex engineering/infrastructure domains? Signup for email updates here!
The Formation of Our Specialist Fusion Team
We're delighted to welcome recent hires Dr Ross Allen and Dr Cyd Cowley. They bring extensive domain expertise from across the fusion ecosystem: plasma science, systems engineering and design, advanced control, and advanced materials/manufacturing.
Ross and Cyd will be partnering with both public and private industry players in order to provide frontline support and guidance for mission-critical applications of ML solutions and our ML platform, twinLab.
Understanding Gaussian Processes, Part 1
At digiLab, we believe that Gaussian Processes are the best option for a wide variety of ML applications in complex engineering/infrastructure domains. They enable you to build highly flexible, probabilistic ML models, with embedded uncertainty quantification, and can handle data which is sparse, limited, noisy, or expensive.
But even if you've been exploring machine learning, there's a good chance you haven't come across Gaussian Processes yet. And if you have, you might have found it difficult to grasp the mathematical intuition behind them.
Attending the 2024 FARSCAPE Workshop
This week, we attended the 2024 FARSCAPE workshop at the UKAEA. FARSCAPE (Fusion Applications Research into Scalable Computing Algorithms for Performance at the Exascale) is a multi-million pound collaboration programme between the UKAEA, the Science and Technology Facilities Council, and digiLab. It aims to simulate fusion power plant systems, and thereby reduce the need for an expensive test-based design approach.
At the workshop, we explored ongoing and future projects involving twinLab, from simulating plasma turbulence to providing uncertainty quantification for engineering systems. We also demonstrated our LLM for accessing fusion information.
Probabilistic ML with twinLab
twinLab is already being used to solve next-generation engineering and sustainability challenges at organisations like the UKAEA, Airbus, and Rolls-Royce. Our vision with twinLab is to help more people and organisations to use probabilistic ML.
Just hit "Try twinLab" at the top-right, or reply to this email, and we'll set you up with an API key, the documentation, and some example solutions.
Alternatively, if you've got a particular data challenge, book a free call with one of our solution engineers.
If you found this post helpful, you might enjoy some of these other news updates.
The Ethical AI Database
digiLab is part of the Ethical AI Database
Dr Andy Corbett
Understanding Uncertainty Quantification: The Different Types
Understanding Uncertainty Quantification - an article on the different types.
Prof Tim Dodwell
Tech Nation Rising Stars 5.0 - delighted national winners!
Tech Nation Rising Stars 5.0 winners
The digiLab Team