Neural Information Processing Systems http://nips.cc/

These methods can be broadly categorized into two types: function learning and operator learning approaches. In function learning, the goal is to directly learn the solution.

Fourier Neural Operators (FNOs) have shown promise for solving partial differential equations (PDEs).

Theperformance ofneural networksonhigh-dimensional datadistributions suggests that it may be possible to parameterize a representation of agiven highdimensional function with controllably small errors, potentially outperforming standard interpolation methods. We demonstrate, both theoretically and numerically, that this is indeed the case. We map the parameters of a neural network to a system of particles relaxing with an interaction potential determined by the lossfunction.