Certain improvements in back propagation procedure for pattern identification

S. N. Sivanandam; M. Paulraj; Mathiyazhagan Nithyanandam

doi:10.1117/12.380559

30 March 2000 Certain improvements in back propagation procedure for pattern identification

S. N. Sivanandam, M. Paulraj, Mathiyazhagan Nithyanandam

Proceedings Volume 4055, Applications and Science of Computational Intelligence III; (2000) https://doi.org/10.1117/12.380559
Event: AeroSense 2000, 2000, Orlando, FL, United States

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.

Citation Download Citation

S. N. Sivanandam, M. Paulraj, and Mathiyazhagan Nithyanandam "Certain improvements in back propagation procedure for pattern identification", Proc. SPIE 4055, Applications and Science of Computational Intelligence III, (30 March 2000); https://doi.org/10.1117/12.380559

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available