Recurrent versus feed-forward neural networks used for identification of non-linear dynamic systems

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F00%3A00000141" target="_blank" >RIV/00216305:26210/00:00000141 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Recurrent versus feed-forward neural networks used for identification of non-linear dynamic systems

Original language description

The paper compaares feed-forward and recurrent neural network architectures use for identification of simple non-linear dynamic system in the terms of generalization abilities, result precision and computational requirements. Comparison has been made ona number of dynamic systems using Elman model as a representative of recurrent networks and various verions of gradient training applied on layered feed-forward networks with one hidden layer.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/VS96122" target="_blank" >VS96122: Resarch Laboratory for Mechatronic Systems</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2000

Confidentiality

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

Article name in the collection

Mechatronics 2000

ISBN

83-914366-0-8

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

—

Publisher name

MEANDER S.C.

Place of publication

Warsaw, Poland

Event location

—

Event date

—

Type of event by nationality

—

UT code for WoS article

—