Relu deep neural networks and linear finite elements

Juncai He, Lin Li, Jinchao Xu, Chunyue Zheng

Research output: Contribution to journalArticlepeer-review

100 Scopus citations

Abstract

In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the simplicial linear finite element method (FEM). We first consider the special case of FEM. By exploring the DNN representation of its nodal basis functions, we present a ReLU DNN representation of CPWL in FEM. We theoretically establish that at least 2 hidden layers are needed in a ReLU DNN to represent any linear finite element functions in Ω ⊆ Rd when d ≥ 2. Consequently, for d = 2, 3 which are often encountered in scientific and engineering computing, the minimal number of two hidden layers are necessary and sufficient for any CPWL function to be represented by a ReLU DNN. Then we include a detailed account on how a general CPWL in Rd can be represented by a ReLU DNN with at most ⌈log2(d + 1)⌉ hidden layers and we also give an estimation of the number of neurons in DNN that are needed in such a representation. Furthermore, using the relationship between DNN and FEM, we theoretically argue that a special class of DNN models with low bit-width are still expected to have an adequate representation power in applications. Finally, as a proof of concept, we present some numerical results for using ReLU DNNs to solve a two point boundary problem to demonstrate the potential of applying DNN for numerical solution of partial differential equations.
Original languageEnglish (US)
Pages (from-to)502-527
Number of pages26
JournalJournal of Computational Mathematics
Volume38
Issue number3
DOIs
StatePublished - Jan 1 2020
Externally publishedYes

ASJC Scopus subject areas

  • Computational Mathematics

Fingerprint

Dive into the research topics of 'Relu deep neural networks and linear finite elements'. Together they form a unique fingerprint.

Cite this