A generalized minimal residual based iterative back propagation algorithm for polynomial nonlinear models

In this paper, a back propagation algorithm is proposed for polynomial nonlinear models using generalized minimal residual method. This algorithm, based on Arnoldi’s method, can be regarded as a modified gradient descent iterative algorithm, and provides several advantages over the traditional gradi...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Systems & control letters Ročník 153; s. 104966
Hlavní autoři:	Chen, Jing, Rong, Yingjiao, Zhu, Quanmin, Chandra, Budi, Zhong, Hongxiu
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 01.07.2021
Témata:	Arnoldi’s method Back propagation Convergence analysis Gradient descent iterative algorithm Nonlinear model Back propagation Gradient descent iterative algorithm Nonlinear model Arnoldi’s method Convergence analysis
ISSN:	0167-6911, 1872-7956
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In this paper, a back propagation algorithm is proposed for polynomial nonlinear models using generalized minimal residual method. This algorithm, based on Arnoldi’s method, can be regarded as a modified gradient descent iterative algorithm, and provides several advantages over the traditional gradient descent iterative algorithm: (1) has less computational efforts for systems with missing data/large-scale systems; (2) does not require the eigenvalue calculation in step-length design; (3) adaptively computes the step-length in each iteration. Therefore, it can be employed for large-scale system identification. The feasibility and effectiveness of the proposed algorithm are established in theory and demonstrated by two simulation examples.
ISSN:	0167-6911 1872-7956
DOI:	10.1016/j.sysconle.2021.104966