🔬“We have foundation models for language, not for physics” — Anima Anandkumar, Bren Professor of Computing
Caltech professor Anima Anandkumar discusses Neural Operators and FourCastNet for physics modeling, arguing inductive biases beat pure token scaling.
Anima Anandkumar, Bren Professor at Caltech and co-founder of Accelerated Understanding, describes Fourier Neural Operators that learn in frequency and spherical-harmonic domains to model weather, fusion, and fluid or heat flow. Her team built FourCastNet 3, a global weather model competitive with physics-based simulations that runs on consumer-grade GPUs. She also introduced TorchLean, a framework for writing PyTorch-style networks inside the Lean proof assistant for formal verification, and was appointed to the United Nations Scientific Advisory Board. She argues physical domains resist scaling due to tiny datasets and context lengths in the hundreds of billions, so progress comes from built-in structure and physical priors.
- Fourier Neural Operator learns in the spherical-harmonic frequency domain for stability
- FourCastNet 3 forecasts global weather competitively with physics simulations on consumer GPUs
- Fusion plasma disruption prediction needs only thousands of samples, about a million times faster than simulation
- TorchLean enables formal verification of PyTorch-style networks inside Lean
- Physical systems resist scaling: limited data and trillion-scale context lengths
- Products
- FourCastNet 3TorchLean
- Organizations
- CaltechUnited NationsLatent Space
- Countries
- United States
- AI models
- FourCastNet
From the original article
4 min read at latent.space
Anima Anandkumar has spent two decades in AI, from classical math to deep learning and back. Now she's using it to model the physical world, from weather to fusion reactors.
By Brandon Anderson · latent.space
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.