Neural Networks Learning Methods Comparison

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F05%3APU52070" target="_blank" >RIV/00216305:26220/05:PU52070 - isvavai.cz</a>

Alternative codes found

RIV/00216305:26210/05:PU54353

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Neural Networks Learning Methods Comparison

Original language description

The paper describes the application of algorithms for object classification by using artificial neural networks. The MLP (Multi Layer Perceptron) neural network was used. We compared results obtained by a using of different learning algorithms - the classical Back propagation algorithm (BP) and the Genetic algorithm (GA). The real technological scene for object classification was simulated with digitization of two-dimensional pictures. The principles and algorithms given below have been used in an appliication that was developed at Brno University of Technology.

Czech name

Porovnání učících metod neuronových sítí

Czech description

The paper describes the application of algorithms for object classification by using artificial neural networks. The MLP (Multi Layer Perceptron) neural network was used. We compared results obtained by a using of different learning algorithms - the classical Back propagation algorithm (BP) and the Genetic algorithm (GA). The real technological scene for object classification was simulated with digitization of two-dimensional pictures. The principles and algorithms given below have been used in an appliication that was developed at Brno University of Technology.

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

<a href="/en/project/GA102%2F03%2F0560" target="_blank" >GA102/03/0560: New methods of providing and monitoring auality of services in next generation networks</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2005

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

WSEAS Transactions on Circuits

ISSN

1109-2734

e-ISSN

—

Volume of the periodical

4

Issue of the periodical within the volume

4

Country of publishing house

GR - GREECE

Number of pages

6

Pages from-to

325-330

UT code for WoS article

—

EID of the result in the Scopus database

—