Scheduled Maintenance on April 29th, 2016:
IEEE Xplore will be unavailable for approximately 1 hour starting at 11:30 AM EDT. We apologize for the inconvenience.
By Topic

Convergence properties of a class of learning vector quantization algorithms

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)
E. B. Kosmatopoulos ; Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece ; M. A. Christodoulou

A mathematical analysis of a class of learning vector quantization (LVQ) algorithms is presented. Using an appropriate time-coordinate transformation, we show that the LVQ algorithms under consideration can be transformed into linear time-varying stochastic difference equations. Using this fact, we apply stochastic Lyapunov stability arguments, and we prove that the LVQ algorithms under consideration do indeed converge, provided that some appropriate conditions hold

Published in:

IEEE Transactions on Image Processing  (Volume:5 ,  Issue: 2 )