Fourier Neural Networks as Function Approximators and Differential Equation Solvers
Abstract
We present a Fourier neural network (FNN) that can be mapped directly to the Fourier decomposition. The choice of activation and loss function yields results that replicate a Fourier series expansion closely while preserving a straightforward architecture with a single hidden layer. The simplicity of this network architecture facilitates the integration with any other higher-complexity networks, at a data pre- or postprocessing stage. We validate this FNN on naturally periodic smooth functions and on piecewise continuous periodic functions. We showcase the use of this FNN for modeling or solving partial differential equations with periodic boundary conditions. The main advantages of the current approach are the validity of the solution outside the training region, interpretability of the trained model, and simplicity of use.
Cite
@article{arxiv.2005.13100,
title = {Fourier Neural Networks as Function Approximators and Differential Equation Solvers},
author = {Marieme Ngom and Oana Marin},
journal= {arXiv preprint arXiv:2005.13100},
year = {2021}
}
Comments
22 pages, 10 figures Added figures to explain the initialization strategy, fixed typos, updated abstract and modified title to make it more self explanatory