FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894744753> ?p ?o ?g. }

• W2894744753 endingPage "57171" @default.
• W2894744753 startingPage "57160" @default.
• W2894744753 abstract "To solve matrix-type linear time-varying equation more efficiently, a novel exponential-type varying gain recurrent neural network (EVG-RNN) is proposed in this paper. Being distinguished from the traditional fixed-parameter gain recurrent neural network (FG-RNN), the proposed EVG-RNN is derived from a vector- or matrix-based unbounded error function by a varying-parameter neural dynamic approach. With four different kinds of activation functions, the super-exponential convergence performance of EVG-RNN is proved theoretically in details, of which the error convergence rate is much faster than that of FG-RNN. In addition, mathematics proves that the computation errors of EVG-RNN can converge to zero, and it possesses the capability of restraining external interference. Finally, series of computer simulations verify and illustrate the better performance of convergence and robustness of EVG-RNN than that of FG-RNN and FTZNN when solving the identical linear time-varying equation." @default.
• W2894744753 created "2018-10-12" @default.
• W2894744753 creator A5044901407 @default.
• W2894744753 creator A5047001937 @default.
• W2894744753 creator A5070652822 @default.
• W2894744753 creator A5084757180 @default.
• W2894744753 date "2018-01-01" @default.
• W2894744753 modified "2023-10-12" @default.
• W2894744753 title "Convergence and Robustness Analysis of the Exponential-Type Varying Gain Recurrent Neural Network for Solving Matrix-Type Linear Time-Varying Equation" @default.
• W2894744753 cites W1488435683 @default.
• W2894744753 cites W1965770068 @default.
• W2894744753 cites W1969196222 @default.
• W2894744753 cites W1983152073 @default.
• W2894744753 cites W1986164962 @default.
• W2894744753 cites W1994504172 @default.
• W2894744753 cites W2000071783 @default.
• W2894744753 cites W2002352814 @default.
• W2894744753 cites W2003162446 @default.
• W2894744753 cites W2013549301 @default.
• W2894744753 cites W2019794318 @default.
• W2894744753 cites W2025098296 @default.
• W2894744753 cites W2035465647 @default.
• W2894744753 cites W2036557378 @default.
• W2894744753 cites W2049852972 @default.
• W2894744753 cites W2060452088 @default.
• W2894744753 cites W2092520467 @default.
• W2894744753 cites W2134778979 @default.
• W2894744753 cites W2296440432 @default.
• W2894744753 cites W2315072896 @default.
• W2894744753 cites W2333215771 @default.
• W2894744753 cites W2390401404 @default.
• W2894744753 cites W2500334081 @default.
• W2894744753 cites W2512861787 @default.
• W2894744753 cites W2560323025 @default.
• W2894744753 cites W2568452074 @default.
• W2894744753 cites W2586662914 @default.
• W2894744753 cites W2728742938 @default.
• W2894744753 cites W2736409683 @default.
• W2894744753 cites W2772861103 @default.
• W2894744753 cites W2791994602 @default.
• W2894744753 cites W2793953252 @default.
• W2894744753 cites W2883330484 @default.
• W2894744753 doi "https://doi.org/10.1109/access.2018.2873616" @default.
• W2894744753 hasPublicationYear "2018" @default.
• W2894744753 type Work @default.
• W2894744753 sameAs 2894744753 @default.
• W2894744753 citedByCount "10" @default.
• W2894744753 countsByYear W28947447532019 @default.
• W2894744753 countsByYear W28947447532020 @default.
• W2894744753 countsByYear W28947447532021 @default.
• W2894744753 countsByYear W28947447532022 @default.
• W2894744753 countsByYear W28947447532023 @default.
• W2894744753 crossrefType "journal-article" @default.
• W2894744753 hasAuthorship W2894744753A5044901407 @default.
• W2894744753 hasAuthorship W2894744753A5047001937 @default.
• W2894744753 hasAuthorship W2894744753A5070652822 @default.
• W2894744753 hasAuthorship W2894744753A5084757180 @default.
• W2894744753 hasBestOaLocation W28947447531 @default.
• W2894744753 hasConcept C103642545 @default.
• W2894744753 hasConcept C104317684 @default.
• W2894744753 hasConcept C106487976 @default.
• W2894744753 hasConcept C126255220 @default.
• W2894744753 hasConcept C134306372 @default.
• W2894744753 hasConcept C154945302 @default.
• W2894744753 hasConcept C159985019 @default.
• W2894744753 hasConcept C162324750 @default.
• W2894744753 hasConcept C185592680 @default.
• W2894744753 hasConcept C18903297 @default.
• W2894744753 hasConcept C192562407 @default.
• W2894744753 hasConcept C2775924081 @default.
• W2894744753 hasConcept C2777299769 @default.
• W2894744753 hasConcept C2777303404 @default.
• W2894744753 hasConcept C28826006 @default.
• W2894744753 hasConcept C33923547 @default.
• W2894744753 hasConcept C41008148 @default.
• W2894744753 hasConcept C47446073 @default.
• W2894744753 hasConcept C50522688 @default.
• W2894744753 hasConcept C50644808 @default.
• W2894744753 hasConcept C55493867 @default.
• W2894744753 hasConcept C63479239 @default.
• W2894744753 hasConcept C86803240 @default.
• W2894744753 hasConceptScore W2894744753C103642545 @default.
• W2894744753 hasConceptScore W2894744753C104317684 @default.
• W2894744753 hasConceptScore W2894744753C106487976 @default.
• W2894744753 hasConceptScore W2894744753C126255220 @default.
• W2894744753 hasConceptScore W2894744753C134306372 @default.
• W2894744753 hasConceptScore W2894744753C154945302 @default.
• W2894744753 hasConceptScore W2894744753C159985019 @default.
• W2894744753 hasConceptScore W2894744753C162324750 @default.
• W2894744753 hasConceptScore W2894744753C185592680 @default.
• W2894744753 hasConceptScore W2894744753C18903297 @default.
• W2894744753 hasConceptScore W2894744753C192562407 @default.
• W2894744753 hasConceptScore W2894744753C2775924081 @default.
• W2894744753 hasConceptScore W2894744753C2777299769 @default.
• W2894744753 hasConceptScore W2894744753C2777303404 @default.
• W2894744753 hasConceptScore W2894744753C28826006 @default.
• W2894744753 hasConceptScore W2894744753C33923547 @default.
• W2894744753 hasConceptScore W2894744753C41008148 @default.

• next