TY - GEN

T1 - Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications

AU - Bukovsky, Ivo

AU - Homma, Noriyasu

AU - Smetana, Ladislav

AU - Rodriguez, Ricardo

AU - Mironovova, Martina

AU - Vrana, Stanislav

PY - 2010

Y1 - 2010

N2 - 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 applications for 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 relatively very 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 implementation.

AB - 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 applications for 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 relatively very 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 implementation.

KW - Convergence to global minimum

KW - Industrial applications

KW - Levenberg-Marquardt

KW - Optimization

KW - Quadratic neural unit

KW - Real time recurrent learning

UR - http://www.scopus.com/inward/record.url?scp=78649889081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649889081&partnerID=8YFLogxK

U2 - 10.1109/COGINF.2010.5599677

DO - 10.1109/COGINF.2010.5599677

M3 - Conference contribution

AN - SCOPUS:78649889081

SN - 9781424480401

T3 - Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010

SP - 556

EP - 560

BT - Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010

T2 - 9th IEEE International Conference on Cognitive Informatics, ICCI 2010

Y2 - 7 July 2010 through 9 July 2010

ER -