Potentials of Quadratic Neural Unit for Applications

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F13%3A00212026" target="_blank" >RIV/68407700:21220/13:00212026 - isvavai.cz</a>
Result on the web
<a href="http://www.igi-global.com/chapter/potentials-quadratic-neural-unit-applications/72791" target="_blank" >http://www.igi-global.com/chapter/potentials-quadratic-neural-unit-applications/72791</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.4018/978-1-4666-2651-5.ch023" target="_blank" >10.4018/978-1-4666-2651-5.ch023</a>

Result language
angličtina
Original language name
Potentials of Quadratic Neural Unit for Applications
Original language description
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 industrial control applicationsfor their solvable 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, and high 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 relativelyvery strong in 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 implement
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)