Approximation of functions from Korobov spaces by deep convolutional neural networks
Open Access
- 7 December 2022
- journal article
- research article
- Published by Springer Nature in Advances in Computational Mathematics
- Vol. 48 (6) , 1-26
Abstract
The efficiency of deep convolutional neural networks (DCNNs) has been demonstrated empirically in many practical applications. In this paper, we establish a theory for approximating functions from Korobov spaces by DCNNs. It verifies rigorously the efficiency of DCNNs in approximating functions of many variables with some variable structures and their abilities in overcoming the curse of dimensionality.Keywords
Funding Information
- University of Sydney
This publication has 21 references indexed in Scilit:
- Deep distributed convolutional neural networks: UniversalityAnalysis and Applications, 2018
- Generalization and Expressivity for Deep NetsIEEE Transactions on Neural Networks and Learning Systems, 2018
- Error bounds for approximations with deep ReLU networksNeural Networks, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A reviewInternational Journal of Automation and Computing, 2017
- Nonparametric Regression Based on Hierarchical Interaction ModelsIEEE Transactions on Information Theory, 2016
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Sparse gridsActa Numerica, 2004
- Approximation properties of a multilayered feedforward artificial neural networkAdvances in Computational Mathematics, 1993
- Multilayer feedforward networks with a nonpolynomial activation function can approximate any functionNeural Networks, 1993