A Smoothing Interval Neural Network
Joint Authors
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2012, Issue 2012 (31 Dec. 2012), pp.1-25, 25 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2012-12-29
Country of Publication
Egypt
No. of Pages
25
Main Subjects
Abstract EN
In many applications, it is natural to use interval data to describe various kinds of uncertainties.
This paper is concerned with an interval neural network with a hidden layer.
For the original interval neural network, it might cause oscillation in the learning procedure as indicated in our numerical experiments.
In this paper, a smoothing interval neural network is proposed to prevent the weights oscillation during the learning procedure.
Here, by smoothing we mean that, in a neighborhood of the origin, we replace the absolute values of the weights by a smooth function of the weights in the hidden layer and output layer.
The convergence of a gradient algorithm for training the smoothing interval neural network is proved.
Supporting numerical experiments are provided.
American Psychological Association (APA)
Yang, Dakun& Wu, Wei. 2012. A Smoothing Interval Neural Network. Discrete Dynamics in Nature and Society،Vol. 2012, no. 2012, pp.1-25.
https://search.emarefa.net/detail/BIM-472987
Modern Language Association (MLA)
Yang, Dakun& Wu, Wei. A Smoothing Interval Neural Network. Discrete Dynamics in Nature and Society No. 2012 (2012), pp.1-25.
https://search.emarefa.net/detail/BIM-472987
American Medical Association (AMA)
Yang, Dakun& Wu, Wei. A Smoothing Interval Neural Network. Discrete Dynamics in Nature and Society. 2012. Vol. 2012, no. 2012, pp.1-25.
https://search.emarefa.net/detail/BIM-472987
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-472987