The Construction and Approximation of the Neural Network with Two Weights
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 a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2014/892653 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850175531052433408 |
|---|---|
| author | Zhiyong Quan Zhengqiu Zhang |
| author_facet | Zhiyong Quan Zhengqiu Zhang |
| author_sort | Zhiyong Quan |
| collection | DOAJ |
| description | 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). |
| format | Article |
| id | doaj-art-c00195fcfa7548129e6efeee7726e1fa |
| institution | OA Journals |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-c00195fcfa7548129e6efeee7726e1fa2025-08-20T02:19:26ZengWileyJournal of Applied Mathematics1110-757X1687-00422014-01-01201410.1155/2014/892653892653The Construction and Approximation of the Neural Network with Two WeightsZhiyong Quan0Zhengqiu Zhang1College of Mathematics, Hunan University, Changsha 410082, ChinaCollege of Mathematics, Hunan University, Changsha 410082, ChinaThe 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).http://dx.doi.org/10.1155/2014/892653 |
| spellingShingle | Zhiyong Quan Zhengqiu Zhang The Construction and Approximation of the Neural Network with Two Weights Journal of Applied Mathematics |
| title | The Construction and Approximation of the Neural Network with Two Weights |
| title_full | The Construction and Approximation of the Neural Network with Two Weights |
| title_fullStr | The Construction and Approximation of the Neural Network with Two Weights |
| title_full_unstemmed | The Construction and Approximation of the Neural Network with Two Weights |
| title_short | The Construction and Approximation of the Neural Network with Two Weights |
| title_sort | construction and approximation of the neural network with two weights |
| url | http://dx.doi.org/10.1155/2014/892653 |
| work_keys_str_mv | AT zhiyongquan theconstructionandapproximationoftheneuralnetworkwithtwoweights AT zhengqiuzhang theconstructionandapproximationoftheneuralnetworkwithtwoweights AT zhiyongquan constructionandapproximationoftheneuralnetworkwithtwoweights AT zhengqiuzhang constructionandapproximationoftheneuralnetworkwithtwoweights |