Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation
In this work, two robust zeroing neural network (RZNN) models are presented for online fast solving of the dynamic Sylvester equation (DSE), by introducing two novel power-versatile activation functions (PVAF), respectively. Differing from most of the zeroing neural network (ZNN) models activated by...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Polish Academy of Sciences
2022-05-01
|
Series: | Bulletin of the Polish Academy of Sciences: Technical Sciences |
Subjects: | |
Online Access: | https://journals.pan.pl/Content/123162/PDF/2937_BPASTS_2022_70_3.pdf |
_version_ | 1798041023679561728 |
---|---|
author | Peng Zhou Mingtao Tan |
author_facet | Peng Zhou Mingtao Tan |
author_sort | Peng Zhou |
collection | DOAJ |
description | In this work, two robust zeroing neural network (RZNN) models are presented for online fast solving of the dynamic Sylvester equation (DSE), by introducing two novel power-versatile activation functions (PVAF), respectively. Differing from most of the zeroing neural network (ZNN) models activated by recently reported activation functions (AF), both of the presented PVAF-based RZNN models can achieve predefined time convergence in noise and disturbance polluted environment. Compared with the exponential and finite-time convergent ZNN models, the most important improvement of the proposed RZNN models is their fixed-time convergence. Their effectiveness and stability are analyzed in theory and demonstrated through numerical and experimental examples. |
first_indexed | 2024-04-11T22:15:42Z |
format | Article |
id | doaj.art-bfda91b739374df48312e4f2833b52a7 |
institution | Directory Open Access Journal |
issn | 2300-1917 |
language | English |
last_indexed | 2024-04-11T22:15:42Z |
publishDate | 2022-05-01 |
publisher | Polish Academy of Sciences |
record_format | Article |
series | Bulletin of the Polish Academy of Sciences: Technical Sciences |
spelling | doaj.art-bfda91b739374df48312e4f2833b52a72022-12-22T04:00:23ZengPolish Academy of SciencesBulletin of the Polish Academy of Sciences: Technical Sciences2300-19172022-05-01703https://doi.org/10.24425/bpasts.2022.141307Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equationPeng Zhou0Mingtao Tan1https://orcid.org/0000-0001-9319-6417College of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, ChinaSchool of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde 415000, ChinaIn this work, two robust zeroing neural network (RZNN) models are presented for online fast solving of the dynamic Sylvester equation (DSE), by introducing two novel power-versatile activation functions (PVAF), respectively. Differing from most of the zeroing neural network (ZNN) models activated by recently reported activation functions (AF), both of the presented PVAF-based RZNN models can achieve predefined time convergence in noise and disturbance polluted environment. Compared with the exponential and finite-time convergent ZNN models, the most important improvement of the proposed RZNN models is their fixed-time convergence. Their effectiveness and stability are analyzed in theory and demonstrated through numerical and experimental examples.https://journals.pan.pl/Content/123162/PDF/2937_BPASTS_2022_70_3.pdfrecurrent neural network (rnn)zeroing neural network (znn)rznnfixed-time convergence |
spellingShingle | Peng Zhou Mingtao Tan Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation Bulletin of the Polish Academy of Sciences: Technical Sciences recurrent neural network (rnn) zeroing neural network (znn) rznn fixed-time convergence |
title | Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation |
title_full | Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation |
title_fullStr | Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation |
title_full_unstemmed | Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation |
title_short | Robust zeroing neural networks with two novel power-versatile activation functions for solving dynamic Sylvester equation |
title_sort | robust zeroing neural networks with two novel power versatile activation functions for solving dynamic sylvester equation |
topic | recurrent neural network (rnn) zeroing neural network (znn) rznn fixed-time convergence |
url | https://journals.pan.pl/Content/123162/PDF/2937_BPASTS_2022_70_3.pdf |
work_keys_str_mv | AT pengzhou robustzeroingneuralnetworkswithtwonovelpowerversatileactivationfunctionsforsolvingdynamicsylvesterequation AT mingtaotan robustzeroingneuralnetworkswithtwonovelpowerversatileactivationfunctionsforsolvingdynamicsylvesterequation |