PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units
Work
Year: 2020
Type: article
Abstract: Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not continuous, which limit... more
Source: Journal of Mathematical Study
Authors Bo Li, Shanshan Tang, Haijun Yu
Institutions Academy of Mathematics and Systems Science, University of Chinese Academy of Sciences, National Center for Mathematics and Interdisciplinary Sciences, Chinese Academy of Sciences
Cites: 31
Cited by: 6
Related to: 10
FWCI: 0.933
Citation percentile (by year/subfield): 68.06
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: gold