FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2169273485> ?p ?o ?g. }

• W2169273485 endingPage "1486" @default.
• W2169273485 startingPage "1471" @default.
• W2169273485 abstract "This paper considers a class of neural networks (NNs) for solving linear programming (LP) problems, convex quadratic programming (QP) problems, and nonconvex QP problems where an indefinite quadratic objective function is subject to a set of affine constraints. The NNs are characterized by constraint neurons modeled by ideal diodes with vertical segments in their characteristic, which enable to implement an exact penalty method. A new method is exploited to address convergence of trajectories, which is based on a nonsmooth Lojasiewicz inequality for the generalized gradient vector field describing the NN dynamics. The method permits to prove that each forward trajectory of the NN has finite length, and as a consequence it converges toward a singleton. Furthermore, by means of a quantitative evaluation of the Lojasiewicz exponent at the equilibrium points, the following results on convergence rate of trajectories are established: (1) for nonconvex QP problems, each trajectory is either exponentially convergent, or convergent in finite time, toward a singleton belonging to the set of constrained critical points; (2) for convex QP problems, the same result as in (1) holds; moreover, the singleton belongs to the set of global minimizers; and (3) for LP problems, each trajectory converges in finite time to a singleton belonging to the set of global minimizers. These results, which improve previous results obtained via the Lyapunov approach, are true independently of the nature of the set of equilibrium points, and in particular they hold even when the NN possesses infinitely many nonisolated equilibrium points." @default.
• W2169273485 created "2016-06-24" @default.
• W2169273485 creator A5044513568 @default.
• W2169273485 creator A5064881566 @default.
• W2169273485 creator A5069809502 @default.
• W2169273485 date "2006-11-01" @default.
• W2169273485 modified "2023-09-27" @default.
• W2169273485 title "Convergence of Neural Networks for Programming Problems via a Nonsmooth &Lstrok;ojasiewicz Inequality" @default.
• W2169273485 cites W1509448450 @default.
• W2169273485 cites W1970081682 @default.
• W2169273485 cites W1981744224 @default.
• W2169273485 cites W2010141219 @default.
• W2169273485 cites W2022922836 @default.
• W2169273485 cites W2069732205 @default.
• W2169273485 cites W2097113878 @default.
• W2169273485 cites W2102227134 @default.
• W2169273485 cites W2113927241 @default.
• W2169273485 cites W2117609097 @default.
• W2169273485 cites W2132021010 @default.
• W2169273485 cites W2145356049 @default.
• W2169273485 cites W2148465339 @default.
• W2169273485 cites W2148993855 @default.
• W2169273485 cites W2156278464 @default.
• W2169273485 cites W2156737647 @default.
• W2169273485 cites W2157976960 @default.
• W2169273485 cites W2160121923 @default.
• W2169273485 cites W4210605524 @default.
• W2169273485 cites W4210718478 @default.
• W2169273485 cites W4247473683 @default.
• W2169273485 doi "https://doi.org/10.1109/tnn.2006.879775" @default.
• W2169273485 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/17131662" @default.
• W2169273485 hasPublicationYear "2006" @default.
• W2169273485 type Work @default.
• W2169273485 sameAs 2169273485 @default.
• W2169273485 citedByCount "92" @default.
• W2169273485 countsByYear W21692734852012 @default.
• W2169273485 countsByYear W21692734852013 @default.
• W2169273485 countsByYear W21692734852014 @default.
• W2169273485 countsByYear W21692734852015 @default.
• W2169273485 countsByYear W21692734852016 @default.
• W2169273485 countsByYear W21692734852017 @default.
• W2169273485 countsByYear W21692734852018 @default.
• W2169273485 countsByYear W21692734852019 @default.
• W2169273485 countsByYear W21692734852020 @default.
• W2169273485 countsByYear W21692734852021 @default.
• W2169273485 countsByYear W21692734852022 @default.
• W2169273485 countsByYear W21692734852023 @default.
• W2169273485 crossrefType "journal-article" @default.
• W2169273485 hasAuthorship W2169273485A5044513568 @default.
• W2169273485 hasAuthorship W2169273485A5064881566 @default.
• W2169273485 hasAuthorship W2169273485A5069809502 @default.
• W2169273485 hasConcept C117354338 @default.
• W2169273485 hasConcept C119857082 @default.
• W2169273485 hasConcept C121332964 @default.
• W2169273485 hasConcept C126255220 @default.
• W2169273485 hasConcept C127162648 @default.
• W2169273485 hasConcept C134306372 @default.
• W2169273485 hasConcept C158622935 @default.
• W2169273485 hasConcept C162324750 @default.
• W2169273485 hasConcept C162392398 @default.
• W2169273485 hasConcept C177067428 @default.
• W2169273485 hasConcept C2777303404 @default.
• W2169273485 hasConcept C2779234561 @default.
• W2169273485 hasConcept C28826006 @default.
• W2169273485 hasConcept C31258907 @default.
• W2169273485 hasConcept C33923547 @default.
• W2169273485 hasConcept C41008148 @default.
• W2169273485 hasConcept C41045048 @default.
• W2169273485 hasConcept C50522688 @default.
• W2169273485 hasConcept C50644808 @default.
• W2169273485 hasConcept C54355233 @default.
• W2169273485 hasConcept C57869625 @default.
• W2169273485 hasConcept C60640748 @default.
• W2169273485 hasConcept C62520636 @default.
• W2169273485 hasConcept C81845259 @default.
• W2169273485 hasConcept C86803240 @default.
• W2169273485 hasConceptScore W2169273485C117354338 @default.
• W2169273485 hasConceptScore W2169273485C119857082 @default.
• W2169273485 hasConceptScore W2169273485C121332964 @default.
• W2169273485 hasConceptScore W2169273485C126255220 @default.
• W2169273485 hasConceptScore W2169273485C127162648 @default.
• W2169273485 hasConceptScore W2169273485C134306372 @default.
• W2169273485 hasConceptScore W2169273485C158622935 @default.
• W2169273485 hasConceptScore W2169273485C162324750 @default.
• W2169273485 hasConceptScore W2169273485C162392398 @default.
• W2169273485 hasConceptScore W2169273485C177067428 @default.
• W2169273485 hasConceptScore W2169273485C2777303404 @default.
• W2169273485 hasConceptScore W2169273485C2779234561 @default.
• W2169273485 hasConceptScore W2169273485C28826006 @default.
• W2169273485 hasConceptScore W2169273485C31258907 @default.
• W2169273485 hasConceptScore W2169273485C33923547 @default.
• W2169273485 hasConceptScore W2169273485C41008148 @default.
• W2169273485 hasConceptScore W2169273485C41045048 @default.
• W2169273485 hasConceptScore W2169273485C50522688 @default.
• W2169273485 hasConceptScore W2169273485C50644808 @default.
• W2169273485 hasConceptScore W2169273485C54355233 @default.
• W2169273485 hasConceptScore W2169273485C57869625 @default.
• W2169273485 hasConceptScore W2169273485C60640748 @default.

• next