English

Approximations with deep neural networks in Sobolev time-space

Machine Learning 2021-01-18 v1 Functional Analysis

Abstract

Solutions of evolution equation generally lies in certain Bochner-Sobolev spaces, in which the solution may has regularity and integrability properties for the time variable that can be different for the space variables. Therefore, in this paper, we develop a framework shows that deep neural networks can approximate Sobolev-regular functions with respect to Bochner-Sobolev spaces. In our work we use the so-called Rectified Cubic Unit (ReCU) as an activation function in our networks, which allows us to deduce approximation results of the neural networks while avoiding issues caused by the non regularity of the most commonly used Rectivied Linear Unit (ReLU) activation function.

Keywords

Cite

@article{arxiv.2101.06115,
  title  = {Approximations with deep neural networks in Sobolev time-space},
  author = {Ahmed Abdeljawad and Philipp Grohs},
  journal= {arXiv preprint arXiv:2101.06115},
  year   = {2021}
}

Comments

34 pages. This is the first version of the paper. It is expected that some changes will be performed for the next version. arXiv admin note: text overlap with arXiv:1902.07896

R2 v1 2026-06-23T22:12:11.492Z