EurekAlert!

Learning neural operators on Riemannian manifolds

While artificial intelligence (AI) has made remarkable achievements in domains like image recognition and natural language processing, it encounters fundamental challenges when trying to deal with ...
EurekAlert!

PIANO: a new operator learning framework that deciphers and incorporates invariants from the PDE series via self-supervised learning and attention technique, achieving superior ...

(a). Given the PDE initial fields, PIANO first infers the physical invariant (PI) embedding via the PI encoder, then integrates it into the neural operator to obtain a personalized operator. After ...
Semiconductor Engineering

3D-IC: Operator Learning Framework For Ultra-Fast 3D Chip Thermal Prediction Under Multiple Chip Design Configurations

A new technical paper titled “DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design” was published (preprint) by researchers at UCSB and Cadence. “Thermal issue is a major ...
mccormick.northwestern.edu

New Machine Learning Framework Enables Data-Efficient Design of Advanced Metamaterials

Until now, designing complex metamaterials with specific mechanical properties required large and costly experimental and simulation datasets. The method enables ...
Quanta Magazine

A New Link to an Old Model Could Crack the Mystery of Deep Learning

In the machine learning world, the sizes of artificial neural networks — and their outsize successes — are creating conceptual conundrums. When a network named AlexNet won an annual image recognition ...