Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F10%3A00173684" target="_blank" >RIV/68407700:21220/10:00173684 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5599677" target="_blank" >http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5599677</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/COGINF.2010.5599677" target="_blank" >10.1109/COGINF.2010.5599677</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications

Popis výsledku v původním jazyce

The paper discusses the quadratic neural unit (QNU) and highlights its attractiveness for industrial applications such as for plant modeling, control, and time series prediction. Linear systems are still often preferred in 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

Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications

Popis výsledku anglicky

The paper discusses the quadratic neural unit (QNU) and highlights its attractiveness for industrial applications such as for plant modeling, control, and time series prediction. Linear systems are still often preferred in 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

D - Stať ve sborníku

CEP obor

BC - Teorie a systémy řízení

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2010

Kód důvěrnosti údajů

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

Název statě ve sborníku

Cognitive Informatics (ICCI), 2010 9th IEEE International Conference on

ISBN

978-1-4244-8040-1

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

556-560

Název nakladatele

IEEE Computer Society Press

Místo vydání

Los Alamitos

Místo konání akce

Beijing

Datum konání akce

7. 7. 2010

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—