Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter

The results of statistical analysis of neural network tuning by LMS-algorithm with square constraint for weight vector jitter are represented. The expressions for correlation function of output signal of neuron of the neural of different network layers are obtained. It is shown, that the weight vect...

Full description

Saved in:
Bibliographic Details
Main Author: S. V. Zimina
Format: Article
Language:Russian
Published: Saint Petersburg Electrotechnical University "LETI" 2015-04-01
Series:Известия высших учебных заведений России: Радиоэлектроника
Subjects:
Online Access:https://re.eltech.ru/jour/article/view/18
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1839584266020716544
author S. V. Zimina
author_facet S. V. Zimina
author_sort S. V. Zimina
collection DOAJ
description The results of statistical analysis of neural network tuning by LMS-algorithm with square constraint for weight vector jitter are represented. The expressions for correlation function of output signal of neuron of the neural of different network layers are obtained. It is shown, that the weight vector jitter leads to distortions of statistical characteristics of neural network and these distortions increase with increasing of number of neural network layer.
format Article
id doaj-art-54433496cfe64b51a403efba67af3388
institution Matheson Library
issn 1993-8985
2658-4794
language Russian
publishDate 2015-04-01
publisher Saint Petersburg Electrotechnical University "LETI"
record_format Article
series Известия высших учебных заведений России: Радиоэлектроника
spelling doaj-art-54433496cfe64b51a403efba67af33882025-08-03T19:50:24ZrusSaint Petersburg Electrotechnical University "LETI"Известия высших учебных заведений России: Радиоэлектроника1993-89852658-47942015-04-0102263218Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitterS. V. Zimina0Lobachevsky state university of Nizhny NovgorodThe results of statistical analysis of neural network tuning by LMS-algorithm with square constraint for weight vector jitter are represented. The expressions for correlation function of output signal of neuron of the neural of different network layers are obtained. It is shown, that the weight vector jitter leads to distortions of statistical characteristics of neural network and these distortions increase with increasing of number of neural network layer.https://re.eltech.ru/jour/article/view/18lms-алгоритм с квадратичным ограничениемneural networkweight vector jitterlms algorithm tuning with square constraint
spellingShingle S. V. Zimina
Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
Известия высших учебных заведений России: Радиоэлектроника
lms-алгоритм с квадратичным ограничением
neural network
weight vector jitter
lms algorithm tuning with square constraint
title Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
title_full Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
title_fullStr Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
title_full_unstemmed Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
title_short Correlative characteristics of the neural network with LMS-algorithm tuning with square constraint with weight vector jitter
title_sort correlative characteristics of the neural network with lms algorithm tuning with square constraint with weight vector jitter
topic lms-алгоритм с квадратичным ограничением
neural network
weight vector jitter
lms algorithm tuning with square constraint
url https://re.eltech.ru/jour/article/view/18
work_keys_str_mv AT svzimina correlativecharacteristicsoftheneuralnetworkwithlmsalgorithmtuningwithsquareconstraintwithweightvectorjitter