Approximation Analysis of Convolutional Neural Networks

Year:    2023

Author:    Chenglong Bao, Qianxiao Li, Zuowei Shen, Cheng Tai, Lei Wu, Xueshuang Xiang

East Asian Journal on Applied Mathematics, Vol. 13 (2023), Iss. 3 : pp. 524–549

Abstract

In its simplest form, convolution neural networks (CNNs) consist of a fully connected two-layer network $g$ composed with a sequence of convolution layers $T.$ Although $g$ is known to have the universal approximation property, it is not known if CNNs, which have the form $g◦T$ inherit this property, especially when the kernel size in $T$ is small. In this paper, we show that under suitable conditions, CNNs do inherit the universal approximation property and its sample complexity can be characterized. In addition, we discuss concretely how the nonlinearity of $T$ can improve the approximation power. Finally, we show that when the target function class has a certain compositional form, convolutional networks are far more advantageous compared with fully connected networks, in terms of the number of parameters needed to achieve the desired accuracy.

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/eajam.2022-270.070123

East Asian Journal on Applied Mathematics, Vol. 13 (2023), Iss. 3 : pp. 524–549

Published online:    2023-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    26

Keywords:    Convolutional networks approximation scaling analysis compositional functions.

Author Details

Chenglong Bao

Qianxiao Li

Zuowei Shen

Cheng Tai

Lei Wu

Xueshuang Xiang