The Ridge Function Representation of Polynomials and an Application to Neural Networks

被引：6

作者：

Xie, Ting Fan ^{[1
]}

Cao, Fei Long ^{[1
]}

机构：

[1] China Jiliang Univ, Dept Informat & Math Sci, Hangzhou 310018, Zhejiang, Peoples R China

来源：

ACTA MATHEMATICA SINICA-ENGLISH SERIES | 2011年 / 27卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Ridge function; neural network; polynomial; approximation; UNIVERSAL APPROXIMATION; ERROR-BOUNDS;

D O I：

10.1007/s10114-011-9407-1

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

The first goal of this paper is to establish some properties of the ridge function representation for multivariate polynomials, and the second one is to apply these results to the problem of approximation by neural networks. We find that for continuous functions, the rate of approximation obtained by a neural network with one hidden layer is no slower than that of an algebraic polynomial.

引用

页码：2169 / 2176

页数：8

共 50 条

[1] The ridge function representation of polynomials and an application to neural networks
Ting Fan Xie
Fei Long Cao
Acta Mathematica Sinica, English Series, 2011, 27 : 2169 - 2176
[2] On a smoothness problem in ridge function representation
Aliev, Rashid A.
Ismailov, Vugar E.
ADVANCES IN APPLIED MATHEMATICS, 2016, 73 : 154 - 169
[3] ON THE HOLDER CONTINUITY IN RIDGE FUNCTION REPRESENTATION
Aliev, Rashid A.
Asgarova, Aysel A.
Ismailov, Vugar E.
PROCEEDINGS OF THE INSTITUTE OF MATHEMATICS AND MECHANICS, 2019, 45 (01): : 31 - 40
[4] Parameter redundancy in neural networks: An application of Chebyshev polynomials
Curry B.
Computational Management Science, 2007, 4 (3) : 227 - 242
[5] Learning Polynomials with Neural Networks
Andoni, Alexandr
Panigrahy, Rina
Valiant, Gregory
Zhang, Li
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 1908 - 1916
[6] The Chebyshev-Polynomials-Based unified model neural networks for function approximation
Lee, TT
Jeng, JT
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (06): : 925 - 935
[7] Approximation by ridge functions and neural networks with a bounded number of neurons
Ismailov, Vugar E.
APPLICABLE ANALYSIS, 2015, 94 (11) : 2245 - 2260
[8] A note on the applications of one primary function in deep neural networks
Chen, Hengjie
Li, Zhong
INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2022, 20 (04)
[9] Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
Li, Yingzhou
Cheng, Xiuyuan
Lu, Jianfeng
COMMUNICATIONS IN COMPUTATIONAL PHYSICS, 2020, 28 (05) : 1838 - 1885
[10] The construction and approximation of neural networks operators with Gaussian activation function
Chen, Zhixiang
Cao, Feilong
MATHEMATICAL COMMUNICATIONS, 2013, 18 (01) : 185 - 207

← 1 2 3 4 5 →