Welcome to the InfoSci Platform
Reference Hub2
Potentials of Quadratic Neural Unit for Applications

Potentials of Quadratic Neural Unit for Applications

Ricardo Rodriguez, Ivo Bukovsky, Noriyasu Homma
Copyright: © 2011 |Volume: 3 |Issue: 3 |Pages: 12
ISSN: 1942-9045|EISSN: 1942-9037|EISBN13: 9781613509197|DOI: 10.4018/ijssci.2011070101
Cite Article Cite Article

MLA

Rodriguez, Ricardo, et al. "Potentials of Quadratic Neural Unit for Applications." IJSSCI vol.3, no.3 2011: pp.1-12. http://doi.org/10.4018/ijssci.2011070101

APA

Rodriguez, R., Bukovsky, I., & Homma, N. (2011). Potentials of Quadratic Neural Unit for Applications. International Journal of Software Science and Computational Intelligence (IJSSCI), 3(3), 1-12. http://doi.org/10.4018/ijssci.2011070101

Chicago

Rodriguez, Ricardo, Ivo Bukovsky, and Noriyasu Homma. "Potentials of Quadratic Neural Unit for Applications," International Journal of Software Science and Computational Intelligence (IJSSCI) 3, no.3: 1-12. http://doi.org/10.4018/ijssci.2011070101

Export Reference

Mendeley
Favorite Full-Issue Download

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. These advantages of QNU are demonstrated by using real and theoretical examples.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.