Autors: Mladenov, V. M.
Title: On the recurrent neural networks for solving general quadratic programming problems
Keywords: Recurrent neural networks , Quadratic programming , Neural n

Abstract: Quadratic programming problems are a widespread class of nonlinear programming problems with many practical applications. The case of inequality constraints have been considered in a previous author's paper. In this contribution, an extension of these results for the case of inequality and equality constraints is presented. Based on an equivalent formulation of the Kuhn-Tucker conditions, a new neural network for solving general quadratic programming problems, for the case of both inequality and equality constraints, is proposed. Two theorems for global stability and convergence of this network are given as well. The presented network has lower complexity for implementations and the examples confirm its effectiveness. Simulation results based on SIMULINK/spl reg/ models are given and compared.

References

    Issue

    Proceedings of the 7th Seminar on Neural Network Applications in Electrical Engineering, NEUREL, pp. 5-9, 2004, Serbia, IEEE, DOI: 10.1109/NEUREL.2004.1416518

    Цитирания (Citation/s):
    1. Yagi, P.A., Quiroz, E.A.P. and Lengua, M.A.C., 2023, August. A Systematic Literature Review on Quadratic Programming. In Proceedings of Seventh International Congress on Information and Communication Technology: ICICT 2022, London, Volume 4 (pp. 739-747). Singapore: Springer Nature Singapore., ISBN 978-981192396-8, DOI 10.1007/978-981-19-2397-5_66 (Web of Science, Scopus, Google Scholar) SJR 0.151 - 2023 - в издания, индексирани в Scopus и/или Web of Science
    2. Elenkov A., 2009, “Virtualization of Virtual Measurement Machines as component of Distributed Artificial Intelligence System,” Proceedings of the 8th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering & Data Bases (AIKED '09), ISSN: 1790-5109, ISBN: 978-960-474-051-2, pp. 21-26, (Google Scholar, Web of Science) - 2009 - в издания, индексирани в Web of Science
    3. Ткаченко Р., Дем'Янчук С., Побудова емпіричних формул за перетворень-Науковий вісник НЛТУ України, 2015 - cyberleninka.ru (Google Scholar) - 2015 - от чужди автори в чужди издания, неиндексирани в Scopus или Web of Science
    4. Yang J., Li Z., A predefined-time convergent low-computational-complexity zeroing neural network for equality-constrained time-varying quadratic programming, 2025, Expert Systems with Applications, issue 0, vol. 293, DOI 10.1016/j.eswa.2025.128692, issn 09574174 - 2025 - в издания, индексирани в Scopus

    Вид: пленарен доклад в международен форум, публикация в реферирано издание, индексирана в Scopus