By Topic

Learning in neural networks by normalized stochastic gradient algorithm: local convergence

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
V. Tadic ; Autom. Control Lab., Mihailo Pupin Inst., Belgrade, Yugoslavia ; S. Stankovic

In this paper, a normalized stochastic gradient algorithm is proposed for learning in feedforward neural networks. By using a new methodology based on the martingale convergence results, asymptotic properties of the algorithm are analyzed. It is proved that, in general, the sequence of the algorithm states converges with probability one to the set of zeroes of the gradient of the criterion function locally on the event where it is bounded. Then, these results are applied to learning in multilayer perceptrons

Published in:

Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on

Date of Conference: