← Papers
Operators

Clifford layers

Clifford Neural Layers for PDE Modeling

Paper title Clifford Neural Layers for PDE Modeling

Brandstetter et al. (Microsoft Research) · Aero & CFD · Electromagnetics · Weather & climate · Public: code

Paper arXiv 2209.04934PDF

Scalar and vector fields at each point are packed into one multivector, and convolutions and Fourier layers act on these multivectors with Clifford algebra, so the coupling between, for example, pressure and velocity components is built into each layer.

Published
ICLR

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. OperatorsTurtLES — A 3D turbulent-wake benchmark where operators fail over long rollouts
  2. OperatorsFunction-space certification — Domain-wide guarantees for neural operators, not only at grid points
  3. OperatorsL-SplineFNO — Learnable splines take the FNO to unstructured meshes