RO  EN
IMI/Publicaţii/CSJM/Ediţii/CSJM v.22, n.1 (64), 2014/

Dynamic Object Identification with SOM-based neural networks

Authors: Aleksey Averkin, Veaceslav Albu, Sergey Ulyanov, Ilya Povidalo
Keywords: Neural networks; forecasting; timeseries prediction; dynamic object identification.

Abstract

In this article a number of neural networks based on selforganizing maps, that can be successfully used for dynamic object identification, is described. Unique SOM-based modular neural networks with vector quantized associative memory and recurrent self-organizing maps as modules are presented. The structured algorithms of learning and operation of such SOM-based neural networks are described in details, also some experimental results and comparison with some other neural networks are given.

Aleksey Averkin
Institution of Russian Academy of Sciences Dorodnicyn Computing Centre of RAS
Vavilov st. 40, 119333 Moscow, Russia
E-mail:

Veaceslav Albu
Institute of Mathematics and Computer Science
Academiei 5, Kishinev, MD 2028 Moldova
E-mail:

Sergey Ulyanov
International University of Nature, Society and Man "Dubna"
Universitetskaya st. 19, 141980 Dubna, Moscow region, Russia
E-mail:

Ilya Povidalo
International University of Nature, Society and Man "Dubna"
Universitetskaya st. 19, 141980 Dubna, Moscow region, Russia
E-mail:



Fulltext

Adobe PDF document0.98 Mb