Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison

In this article, a benchmark of algorithms for training of piecewise-linear artificial neural networks is introduced. At first, motivation of this article is described for a special topology of the neural network is used. This topology can be advantageously used in system control design, but it is...

Full description

Bibliographic Details
Main Authors:	Martin MARIŠKA, Petr DOLEŽEL
Format:	Article
Language:	English
Published:	VSB-Technical University of Ostrava 2013-12-01
Series:	Transactions of the VSB : Technical University of Ostrava
Subjects:	piecewise-linear neural network benchmark machine-learning algorithms process control
Online Access:	http://transactions.fs.vsb.cz/2013-2/1965.pdf

id	doaj-bf6a04973898400baacf1673a4813dc1
record_format	Article
spelling	doaj-bf6a04973898400baacf1673a4813dc12020-11-25T00:02:29ZengVSB-Technical University of OstravaTransactions of the VSB : Technical University of Ostrava1210-04711804-09932013-12-0159212112610.22223/tr.2013-2/1965Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency ComparisonMartin MARIŠKA0Petr DOLEŽEL1University of PardubiceUniversity of PardubiceIn this article, a benchmark of algorithms for training of piecewise-linear artificial neural networks is introduced. At first, motivation of this article is described for a special topology of the neural network is used. This topology can be advantageously used in system control design, but it is difficult problem to train it. In this article, there is described a set of possible training algorithms, these algorithms are tested and evaluated. Benchmarking data are based on real problems.http://transactions.fs.vsb.cz/2013-2/1965.pdfpiecewise-linear neural networkbenchmarkmachine-learning algorithmsprocess control
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Martin MARIŠKA Petr DOLEŽEL
spellingShingle	Martin MARIŠKA Petr DOLEŽEL Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison Transactions of the VSB : Technical University of Ostrava piecewise-linear neural network benchmark machine-learning algorithms process control
author_facet	Martin MARIŠKA Petr DOLEŽEL
author_sort	Martin MARIŠKA
title	Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison
title_short	Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison
title_full	Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison
title_fullStr	Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison
title_full_unstemmed	Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison
title_sort	piecewise-linear neural network – possible training algorithms efficiency comparison
publisher	VSB-Technical University of Ostrava
series	Transactions of the VSB : Technical University of Ostrava
issn	1210-0471 1804-0993
publishDate	2013-12-01
description	In this article, a benchmark of algorithms for training of piecewise-linear artificial neural networks is introduced. At first, motivation of this article is described for a special topology of the neural network is used. This topology can be advantageously used in system control design, but it is difficult problem to train it. In this article, there is described a set of possible training algorithms, these algorithms are tested and evaluated. Benchmarking data are based on real problems.
topic	piecewise-linear neural network benchmark machine-learning algorithms process control
url	http://transactions.fs.vsb.cz/2013-2/1965.pdf
work_keys_str_mv	AT martinmariska piecewiselinearneuralnetworkpossibletrainingalgorithmsefficiencycomparison AT petrdolezel piecewiselinearneuralnetworkpossibletrainingalgorithmsefficiencycomparison
_version_	1725437474626338816

Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison

Similar Items