DocumentCode
3316295
Title
Fast Terminal Attractor Based Backpropagation Algorithm For Feedforward Neural Networks
Author
Batbayar, Batsukh ; Yu, Xinghuo
Author_Institution
R. Melbourne Inst. of Technol., Melbourne
fYear
2007
fDate
3-6 Dec. 2007
Firstpage
521
Lastpage
525
Abstract
In this paper, a new efficient fast terminal attractor based backpropagation learning algorithm for feedforward neural networks is proposed, which improves the convergence speed. The effectiveness of the proposed algorithm in improving learning speed is shown by the simulation results including a sensor network example.
Keywords
backpropagation; feedforward neural nets; backpropagation learning; convergence speed; fast terminal attractor; feedforward neural networks; learning speed; Australia; Backpropagation algorithms; Computational modeling; Computer networks; Convergence; Data mining; Feedforward neural networks; Function approximation; Neural networks; Pattern recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Sensors, Sensor Networks and Information, 2007. ISSNIP 2007. 3rd International Conference on
Conference_Location
Melbourne, Qld.
Print_ISBN
978-1-4244-1501-4
Electronic_ISBN
978-1-4244-1502-1
Type
conf
DOI
10.1109/ISSNIP.2007.4496897
Filename
4496897
Link To Document