Title :
Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications
Author :
Bukovsky, Ivo ; Homma, Noriyasu ; Smetana, Ladislav ; Rodriguez, Ricardo ; Mironovova, Martina ; Vrana, Stanislav
Author_Institution :
Czech Tech. Univ. in Prague, Prague, Czech Republic
Abstract :
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.
Keywords :
cognitive systems; industrial control; learning (artificial intelligence); linear systems; neurocontrollers; nonlinear control systems; optimisation; time series; application correct neural architecture; cognitive nonlinear tool; industrial control application; linear system; local minima problem; nonlinear approximation; nonlinear neural network; optimization technique; plant control; plant modeling; quadratic neural unit; time series prediction; Adaptive systems; Artificial neural networks; Book reviews; Mathematical model; Optimization; Recurrent neural networks; Training; Levenberg-Marquardt; convergence to global minimum; industrial applications; optimization; quadratic neural unit; real time recurrent learning;
Conference_Titel :
Cognitive Informatics (ICCI), 2010 9th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-8041-8
DOI :
10.1109/COGINF.2010.5599677