Machine learning models are being used more and more widely. However, they need a lot of training data to deliver good results. In industrial applications, this wealth of data is often not available ...

Researchers use statistical physics and "toy models" to explain how neural networks avoid overfitting and stabilize learning in high-dimensional spaces.

Physicists at Harvard University have developed a simplified, physics-inspired mathematical model to better understand how neural networks learn, potentially explaining why large AI systems often ...

A case study in aerospace manufacturing provides an overview of how physics-informed digital twin systems transform robotics processes—from adaptive process planning and real-time process monitoring ...

A new study in Science Advances shows that physics-based weather models, like HRES, outperform leading AI systems when predicting record-breaking extreme events. While AI models such as GraphCast and ...

Abstract: Elastomers and polymers such as silicone and Kapton have a wide range of applications across engineering disciplines, including structural components and thermal shields in space structures.

Abstract: The AFOSR MURI effort, titled “A Robust Multi-Physics Design Analysis and Optimization Framework for Hypersonic Systems Grounded in Rigorous Model Reduction,” unites a multi-disciplinary ...

For decades, scientists have relied on structure to understand protein function. Tools like AlphaFold have revolutionized how researchers predict and design folded proteins, allowing for new ...