Share Email Print

Proceedings Paper

Certain improvements in back propagation procedure for pattern identification
Author(s): S. N. Sivanandam; M. Paulraj; Mathiyazhagan Nithyanandam
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper certain simple procedures are presented for stabilization of a class of NN trained by Back Propagation algorithm with minimum number of failures. To quicken the network response with minimum number of oscillations, a slope parameter is utilized in the bipolar sigmoidal activation function and is appropriately chosen with the help of Lyapunov's stability theorem. Further a new weight update scheme is proposed for the backpropagation algorithm. The above procedures are applied and tested with XOR problem, Iris data and image data for the choices of slope parameter, learning rate and momentum factor; its performance in terms of local minima, learning speed are evaluated and compared with the performance of traditional BP algorithm.

Paper Details

Date Published: 30 March 2000
PDF: 11 pages
Proc. SPIE 4055, Applications and Science of Computational Intelligence III, (30 March 2000); doi: 10.1117/12.380559
Show Author Affiliations
S. N. Sivanandam, PSG College of Technology (India)
M. Paulraj, PSG College of Technology (India)
Mathiyazhagan Nithyanandam, IMR Global Corp. (United States)

Published in SPIE Proceedings Vol. 4055:
Applications and Science of Computational Intelligence III
Kevin L. Priddy; Paul E. Keller; David B. Fogel, Editor(s)

© SPIE. Terms of Use
Back to Top