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

Ivo Bukovsky, Noriyasu Homma, Ladislav Smetana, Ricardo Rodriguez, Martina Mironovova, Stanislav Vrana

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010
Pages556-560
Number of pages5
DOIs
Publication statusPublished - 2010
Event9th IEEE International Conference on Cognitive Informatics, ICCI 2010 - Beijing, China
Duration: 2010 Jul 72010 Jul 9

Publication series

NameProceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010

Other

Other9th IEEE International Conference on Cognitive Informatics, ICCI 2010
CountryChina
CityBeijing
Period10/7/710/7/9

Keywords

  • Convergence to global minimum
  • Industrial applications
  • Levenberg-Marquardt
  • Optimization
  • Quadratic neural unit
  • Real time recurrent learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Fingerprint Dive into the research topics of 'Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications'. Together they form a unique fingerprint.

  • Cite this

    Bukovsky, I., Homma, N., Smetana, L., Rodriguez, R., Mironovova, M., & Vrana, S. (2010). Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications. In Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010 (pp. 556-560). [5599677] (Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010). https://doi.org/10.1109/COGINF.2010.5599677