Resources

Whitepapers

Picture of an application of PhysicsX's technology
Transforming Engineering with AI – An Introduction to PhysicsX
Discover how PhysicsX empowers engineers to revolutionize design, manufacturing, and operation processes with AI-driven, real-time simulations, unlocking unprecedented performance and efficiency across advanced industries like aerospace, automotive, and renewable energy.
Picture of an application of PhysicsX's technology
From Pilots to Partnership: Identifying effective pilots
In this article we explain how we partner with customers to tackle critical engineering problems through strategic and collaborative pilots. You will find details about our process – from identifying real-world challenges to deploying multi-disciplinary teams that work side-by-side with customer engineers. Learn how we ensure pilots are immediately valuable, short-term, and focused on clear, measurable outcomes.

Research

A grid of chart on Uncertainty Quantification
On machine learning methods for physics
At PhysicsX, we believe that machine learning methods will fundamentally transform the landscape of physical simulation, making it more efficient and powerful than ever before.Read our Research team’s perspective on how this transformation is taking place and on the most promising approaches

Read the full article | Read on Medium
A grid of chart on Uncertainty Quantification
Uncertainty quantification in artificial neural networks: an overview
Our research team, led by Michalis Michaelides, offers a valuable perspective on incorporating quantified uncertainties into Artificial Neural Network (ANN) models. Understanding and quantifying uncertainty is crucial for effective optimization and principled decision-making. In our latest piece, we outline accessible methods for integrating uncertainty quantification into ANNs. Explore the details and the broader landscape of this intriguing topic.

Read the full article | Read on Medium

Blog

A person working on their laptop
Write Fast, Efficient, and Production-Ready PyTorch Deep Learning Models
In this insightful journey, Axen Georget – one of our Product Machine Learning Engineers – unravels the complexities of Deep Learning using Python and PyTorch. The focus is on streamlining the transition from experiments to production-ready models, emphasizing speed, efficiency, and industry best practices. Designed to narrow the gap between experimental and product-ready models, this 4-part series is tailored for individuals with a background in machine learning and programming.

Read the full series on Medium
A person working on their laptop
A conversation about AI-powered simulation with Simcenter
Robin Tuluie (Founder, Chief Science and Engineering Officer) and  Nicolas Haag (Co-founder and Director of Engineering) joined Stephen Ferguson on Simcenter's podcast on CAE and Engineering AI/ML, discussing how we are combining AI and engineering while empowering organisations to enable breakthrough engineering.

Listen to the episode here