The Construction and Approximation of the Neural Network with Two Weights

被引：1

作者：

Quan, Zhiyong ^{[1
]}

Zhang, Zhengqiu ^{[1
]}

机构：

[1] Hunan Univ, Coll Math, Changsha 410082, Hunan, Peoples R China

来源：

JOURNAL OF APPLIED MATHEMATICS | 2014年

关键词：

SIGMOIDAL FUNCTIONS; OPERATORS;

D O I：

10.1155/2014/892653

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

The technique of approximate partition of unity, the way of Fourier series, and inequality technique are used to construct a neural network with two weights and with sigmoidal functions. Furthermore by using inequality technique, we prove that the neural network with two weights can more precisely approximate any nonlinear continuous function than BP neural network constructed in (Chen et al., 2012).

引用

页数：6

共 50 条

[1] The Estimate for Approximation Error of Neural Network with Two Weights
Zeng, Fanzi
Tang, Yuting
SCIENTIFIC WORLD JOURNAL, 2013,
[2] The Construction and Approximation of ReLU Neural Network Operators
Chen, Hengjie
Yu, Dansheng
Li, Zhong
JOURNAL OF FUNCTION SPACES, 2022, 2022
[3] Approximation capabilities of neural networks with weights from two directions
Ismailov, V. E.
AZERBAIJAN JOURNAL OF MATHEMATICS, 2011, 1 (01): : 122 - 128
[4] Channel equalization based on two weights neural network
Cao, WM
Chai, WF
Wang, SJ
COMPUTATIONAL INTELLIGENCE AND SECURITY, PT 2, PROCEEDINGS, 2005, 3802 : 1068 - 1073
[5] Two Neural Network Construction Methods
G. Thimm
E. Fiesler
Neural Processing Letters, 1997, 6 : 25 - 31
[6] Two neural network construction methods
Thimm, G
Fiesler, E
NEURAL PROCESSING LETTERS, 1997, 6 (1-2) : 25 - 31
[7] Approximation capability of two hidden layer feedforward neural networks with fixed weights
Guliyev, Namig J.
Ismailov, Vugar E.
NEUROCOMPUTING, 2018, 316 : 262 - 269
[8] The construction and approximation of feedforward neural network with hyperbolic tangent function
Chen Zhi-xiang
Cao Fei-long
APPLIED MATHEMATICS-A JOURNAL OF CHINESE UNIVERSITIES SERIES B, 2015, 30 (02) : 151 - 162
[9] The construction and approximation of feedforward neural network with hyperbolic tangent function
CHEN Zhixiang
CAO Feilong
Applied Mathematics:A Journal of Chinese Universities(Series B), 2015, 30 (02) : 151 - 162
[10] The construction and approximation of feedforward neural network with hyperbolic tangent function
CHEN Zhi-xiang
CAO Fei-long
Applied Mathematics:A Journal of Chinese Universities, 2015, (02) : 151 - 162

← 1 2 3 4 5 →