Possibilities of Piecewise-Linear Neural Network Training Using Levenberg-Marquardt Algorithm and Hybrid Differential Evolution
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F16%3A39901988" target="_blank" >RIV/00216275:25530/16:39901988 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Possibilities of Piecewise-Linear Neural Network Training Using Levenberg-Marquardt Algorithm and Hybrid Differential Evolution
Original language description
This article is focused on the comparison of the learning of an artificial neural network with a hyperbolic tangent activation function and an artificial neural network with a linear saturated activation function in hidden layers. The learning is performed by a Levenberg-Marquardt algorithm and hybrid differential evolution. For evaluating of learning characteristics, there is calculated a comprehensive set of statistical variables. The results are analysed and shown as a table for each experiment. An empirical result discussed at the end of the paper is, that the approximation qualities of both networks under examination are similar.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BD - Information theory
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Mendel 2016 : 22nd International Conference on Soft Computing
ISBN
978-80-214-5365-4
ISSN
1803-3814
e-ISSN
—
Number of pages
4
Pages from-to
39-42
Publisher name
Vysoké učení technické v Brně
Place of publication
Brno
Event location
Brno
Event date
Jun 8, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—