The Estimate for Approximation Error of Neural Network with Two Weights
Joint Authors
Source
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-4, 4 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-12-28
Country of Publication
Egypt
No. of Pages
4
Main Subjects
Medicine
Information Technology and Computer Science
Abstract EN
The neural network with two weights is constructed and its approximation ability to any continuous functions is proved.
For this neural network, the activation function is not confined to the odd functions.
We prove that it can limitlessly approach any continuous function from limited close subset of Rm to Rn and any continuous function, which has limit at infinite place, from limitless close subset of Rm to Rn.
This extends the nonlinear approximation ability of traditional BP neural network and RBF neural network.
American Psychological Association (APA)
Zeng, Fanzi& Tang, Yuting. 2013. The Estimate for Approximation Error of Neural Network with Two Weights. The Scientific World Journal،Vol. 2013, no. 2013, pp.1-4.
https://search.emarefa.net/detail/BIM-1033455
Modern Language Association (MLA)
Zeng, Fanzi& Tang, Yuting. The Estimate for Approximation Error of Neural Network with Two Weights. The Scientific World Journal No. 2013 (2013), pp.1-4.
https://search.emarefa.net/detail/BIM-1033455
American Medical Association (AMA)
Zeng, Fanzi& Tang, Yuting. The Estimate for Approximation Error of Neural Network with Two Weights. The Scientific World Journal. 2013. Vol. 2013, no. 2013, pp.1-4.
https://search.emarefa.net/detail/BIM-1033455
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1033455