Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems

Abstract A special recurrent neural network (RNN), that is the zeroing neural network (ZNN), is adopted to find solutions to time‐varying quadratic programming (TVQP) problems with equality and inequality constraints. However, there are some weaknesses in activation functions of traditional ZNN mode...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaoyan Zhang, Liangming Chen, Shuai Li, Predrag Stanimirović, Jiliang Zhang, Long Jin
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/a9918134877d4dea9872592f5f9a307a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a9918134877d4dea9872592f5f9a307a
record_format	dspace
spelling	oai:doaj.org-article:a9918134877d4dea9872592f5f9a307a2021-11-17T03:12:43ZDesign and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems2468-232210.1049/cit2.12019https://doaj.org/article/a9918134877d4dea9872592f5f9a307a2021-12-01T00:00:00Zhttps://doi.org/10.1049/cit2.12019https://doaj.org/toc/2468-2322Abstract A special recurrent neural network (RNN), that is the zeroing neural network (ZNN), is adopted to find solutions to time‐varying quadratic programming (TVQP) problems with equality and inequality constraints. However, there are some weaknesses in activation functions of traditional ZNN models, including convex restriction and redundant formulation. With the aid of different activation functions, modified ZNN models are obtained to overcome the drawbacks for solving TVQP problems. Theoretical and experimental research indicate that the proposed models are better and more effective at solving such TVQP problems.Xiaoyan ZhangLiangming ChenShuai LiPredrag StanimirovićJiliang ZhangLong JinWileyarticleComputational linguistics. Natural language processingP98-98.5Computer softwareQA76.75-76.765ENCAAI Transactions on Intelligence Technology, Vol 6, Iss 4, Pp 394-404 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765
spellingShingle	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765 Xiaoyan Zhang Liangming Chen Shuai Li Predrag Stanimirović Jiliang Zhang Long Jin Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
description	Abstract A special recurrent neural network (RNN), that is the zeroing neural network (ZNN), is adopted to find solutions to time‐varying quadratic programming (TVQP) problems with equality and inequality constraints. However, there are some weaknesses in activation functions of traditional ZNN models, including convex restriction and redundant formulation. With the aid of different activation functions, modified ZNN models are obtained to overcome the drawbacks for solving TVQP problems. Theoretical and experimental research indicate that the proposed models are better and more effective at solving such TVQP problems.
format	article
author	Xiaoyan Zhang Liangming Chen Shuai Li Predrag Stanimirović Jiliang Zhang Long Jin
author_facet	Xiaoyan Zhang Liangming Chen Shuai Li Predrag Stanimirović Jiliang Zhang Long Jin
author_sort	Xiaoyan Zhang
title	Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
title_short	Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
title_full	Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
title_fullStr	Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
title_full_unstemmed	Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
title_sort	design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/a9918134877d4dea9872592f5f9a307a
work_keys_str_mv	AT xiaoyanzhang designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems AT liangmingchen designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems AT shuaili designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems AT predragstanimirovic designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems AT jiliangzhang designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems AT longjin designandanalysisofrecurrentneuralnetworkmodelswithnonlinearactivationfunctionsforsolvingtimevaryingquadraticprogrammingproblems
_version_	1718426008579735552

Design and analysis of recurrent neural network models with non‐linear activation functions for solving time‐varying quadratic programming problems

Ejemplares similares