Fourier Neural Operator
A neural operator method based on the Fourier transform that learns mappings between function spaces and is used to solve partial differential equations efficiently.
Timeline (last 90 days)
Physical AI emphasizes embedding physical constraints such as mass conservation, momentum equations and boundary conditions into machine learning models, and common approaches include physics-informed neural networks (PINN), operator learning (such as the Fourier Neural Operator), and using numerical solvers as differentiable layers.
The Fourier Neural Operator (FNO) was proposed by Li et al. in 2021, and its core innovation lies in transferring operator learning from physical space to the frequency domain, with each layer containing a Fourier transform, a linear transform in the frequency domain, and an inverse Fourier transform.
The parameter count of FNO is decoupled from the grid resolution, and a trained model can perform inference at different resolutions, a property known as 'discretization invariance'.
All Facts (3)
Physical AI emphasizes embedding physical constraints such as mass conservation, momentum equations and boundary conditions into machine learning models, and common approaches include physics-informed neural networks (PINN), operator learning (such as the Fourier Neural Operator), and using numerical solvers as differentiable layers.
50%UnverifiedThe Fourier Neural Operator (FNO) was proposed by Li et al. in 2021, and its core innovation lies in transferring operator learning from physical space to the frequency domain, with each layer containing a Fourier transform, a linear transform in the frequency domain, and an inverse Fourier transform.
50%UnverifiedThe parameter count of FNO is decoupled from the grid resolution, and a trained model can perform inference at different resolutions, a property known as 'discretization invariance'.
50%