Sorry, this article is only available in Русский.
UDC 004.41
NETWORK TRAINING FOR DETECTING FIGURES VIA BUILDING SELF-ORGANAZING MAPS AND THE KOHONEN METHOD
Shchukova Kristina Borisovna
National Research Tomsk Polytechnic University
National Research Tomsk Polytechnic University
Abstract
The article deals with the one of the optimization tasks. The task is to detect figures from 0 to 9 via network training by the Kohonen method.
The self-organizing map structure and its buiding process has been considered in details. The method of data normalization for applying the Kohonen method is discussed. The program by the C# has been developed in which the network has been implemented.
Keywords: C#
Article reference:
Network training for detecting figures via building self-organazing maps and the Kohonen method // Modern technics and technologies. 2015. № 11 [Electronic journal]. URL: https://technology.snauka.ru/en/2015/11/8191
View this article in Russian
© If you have found a violation of copyrights please notify us immediately by e-mail or feedback form.
Contact author (comments/reviews)
Write comment
You must authorise to write a comment.
Если Вы еще не зарегистрированы на сайте, то Вам необходимо зарегистрироваться: