Huge thanks to the team: Zhikai Wu, Shiyang Zhang, Sizhuang He, Sifan Wang, Min Zhu, Anran Jiao, Lu Lu! Let us know what you think! #OperatorLearning #LLM #AI4Science

Hello #FAU. Thanks for the quick plan to host me and letting me present our exciting mathematics of ML in infinite-dimensions, #operatorlearning. #sciML Their "Pattern Recognition Laboratory" is completing 50 years! @andreasmaier.bsky.social 💥

An operator learning framework (oNLI) can reconstruct magnetic resonance elastography images in real time, achieving a 30,000‑fold speed increase. Read more: https://getnews.me/real-time-magnetic-resonance-elastography-via-operator-learning/ #magneticresonance #operatorlearning

DeepONet can be trained to solve many nonlinear PDEs without a separate model per equation; a deeper branch network boosts accuracy while a simple trunk keeps stability. https://getnews.me/deeponet-advances-physics-informed-solving-of-nonlinear-pdes/ #deeponet #operatorlearning

GenUQ adds likelihood‑free uncertainty to operator learning via a generative hyper‑network, outperforming classic Bayesian methods on three benchmark tasks. https://getnews.me/genuq-generative-hyper-networks-for-uncertainty-in-operator-learning/ #operatorlearning #uncertainty

Physics‑informed DeepONet reduces model complexity to a single regularization term, achieving 0.766 correlation (vs 0.770 baseline) and cutting training overhead by ~4%. https://getnews.me/physics-informed-operator-learning-improves-wearable-blood-pressure/ #wearable #bloodpressure #operatorlearning

Principled Approaches for Extending Neural Architectures to Function
Spaces for Operator Learning
Anima Anandkumar, Boris Bonev et al.
Paper
Details
#NeuralArchitectures #OperatorLearning #MachineLearningResearch