Incremental learning of auto-association multilayer perceptrons network
Author
Source
The International Arab Journal of Information Technology
Issue
Vol. 3, Issue 1 (31 Jan. 2006), pp.16-19, 4 p.
Publisher
Publication Date
2006-01-31
Country of Publication
Jordan
No. of Pages
4
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
This paper introduces a new algorithm to reduce the time of updating the weights of auto-association multilayer perceptrons network.
The basic idea is to modify the singular value decomposition which has been used in the batch algorithm to update the weights whenever a new row is added to the input matrix.
The computation analysis and the experiments show that the new algorithm speeds up the implementation about 5-8 times.
American Psychological Association (APA)
al-Daoud, Isam. 2006. Incremental learning of auto-association multilayer perceptrons network. The International Arab Journal of Information Technology،Vol. 3, no. 1, pp.16-19.
https://search.emarefa.net/detail/BIM-11754
Modern Language Association (MLA)
al-Daoud, Isam. Incremental learning of auto-association multilayer perceptrons network. The International Arab Journal of Information Technology Vol. 3, no. 1 (Jan. 2006), pp.16-19.
https://search.emarefa.net/detail/BIM-11754
American Medical Association (AMA)
al-Daoud, Isam. Incremental learning of auto-association multilayer perceptrons network. The International Arab Journal of Information Technology. 2006. Vol. 3, no. 1, pp.16-19.
https://search.emarefa.net/detail/BIM-11754
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 19
Record ID
BIM-11754