Corpus ID: 227253926

Some observations on partial differential equations in Barron and multi-layer spaces

@article{Weinan2020SomeOO,
  title={Some observations on partial differential equations in Barron and multi-layer spaces},
  author={E. Weinan and Stephan Wojtowytsch},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.01484}
}
We use explicit representation formulas to show that solutions to certain partial differential equations can be represented efficiently using artificial neural networks, even in high dimension. Conversely, we present examples in which the solution fails to lie in the function space associated to a neural network under consideration. 
2 Citations
A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
  • 5
  • PDF

References

SHOWING 1-10 OF 25 REFERENCES
Representation formulas and pointwise properties for Barron functions
  • 13
  • PDF
Solving high-dimensional partial differential equations using deep learning
  • 438
  • PDF
...
1
2
3
...