Potentials of Quadratic Neural Unit for Applications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F11%3A00185582" target="_blank" >RIV/68407700:21220/11:00185582 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.igi-global.com/article/potentials-quadratic-neural-unit-applications/60745" target="_blank" >http://www.igi-global.com/article/potentials-quadratic-neural-unit-applications/60745</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.4018/IJSSCI.2011070101" target="_blank" >10.4018/IJSSCI.2011070101</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Potentials of Quadratic Neural Unit for Applications

Popis výsledku v původním jazyce

The paper discusses the quadratic neural unit (QNU) and its attractiveness for industrial applications such as for plant modeling, control, and time series prediction. Linear systems are still often preferred in industrial control applications for theirsolvable and single solution nature and for the clarity to the most application engineers. Artificial neural networks are powerful cognitive nonlinear tools, but their nonlinear strength is naturally repaid with the local minima problem, overfitting, andhigh demands for application-correct neural architecture and optimization technique that often require skilled users. The QNU is the important midpoint between linear systems and highly nonlinear neural networks because the QNU is relatively very strongin nonlinear approximation; however, its optimization and performance have fast and convex-like nature, and its mathematical structure and the derivation of the learning rules is very comprehensible and efficient for implementation.

Název v anglickém jazyce

Potentials of Quadratic Neural Unit for Applications

Popis výsledku anglicky

The paper discusses the quadratic neural unit (QNU) and its attractiveness for industrial applications such as for plant modeling, control, and time series prediction. Linear systems are still often preferred in industrial control applications for theirsolvable and single solution nature and for the clarity to the most application engineers. Artificial neural networks are powerful cognitive nonlinear tools, but their nonlinear strength is naturally repaid with the local minima problem, overfitting, andhigh demands for application-correct neural architecture and optimization technique that often require skilled users. The QNU is the important midpoint between linear systems and highly nonlinear neural networks because the QNU is relatively very strongin nonlinear approximation; however, its optimization and performance have fast and convex-like nature, and its mathematical structure and the derivation of the learning rules is very comprehensible and efficient for implementation.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

BC - Teorie a systémy řízení

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název periodika

International Journal of Software Science and Computational Intelligence (IJSSCI)

ISSN

1942-9045

e-ISSN

—

Svazek periodika

3

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

1-12

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—