FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2049202684> ?p ?o ?g. }

• W2049202684 endingPage "2548" @default.
• W2049202684 startingPage "2536" @default.
• W2049202684 abstract "In this paper, we propose a new neural network architecture based on a family of referential multilayer perceptrons (RMLPs) that play a role of generalized receptive fields. In contrast to ''standard'' radial basis function (RBF) neural networks, the proposed topology of the network offers a considerable level of flexibility as the resulting receptive fields are highly diversified and capable of adjusting themselves to the characteristics of the locally available experimental data. We discuss in detail a design strategy of the novel architecture that fully exploits the modeling capabilities of the contributing RMLPs. The strategy comprises three phases. In the first phase, we form a ''blueprint'' of the network by employing a specialized version of the commonly encountered fuzzy C-means (FCM) clustering algorithm, namely the conditional (context-based) FCM. In this phase our intent is to generate a collection of information granules (fuzzy sets) in the space of input and output variables, narrowed down to some certain contexts. In the second phase, based upon a global view at the structure, we refine the input-output relationships by engaging a collection of RMLPs where each RMLP is trained by using the subset of data associated with the corresponding context fuzzy set. During training each receptive field focuses on the characteristics of these locally available data and builds a nonlinear mapping in a referential mode. Finally, the connections of the receptive fields are optimized through global minimization of the linear aggregation unit located at the output layer of the overall architecture. We also include a series of numeric experiments involving synthetic and real-world data sets which provide a thorough comparative analysis with standard RBF neural networks." @default.
• W2049202684 created "2016-06-24" @default.
• W2049202684 creator A5003799782 @default.
• W2049202684 creator A5019498183 @default.
• W2049202684 creator A5040911847 @default.
• W2049202684 creator A5057031606 @default.
• W2049202684 date "2009-06-01" @default.
• W2049202684 modified "2023-09-27" @default.
• W2049202684 title "Using multilayer perceptrons as receptive fields in the design of neural networks" @default.
• W2049202684 cites W1594640477 @default.
• W2049202684 cites W1963581687 @default.
• W2049202684 cites W1977516301 @default.
• W2049202684 cites W1985582583 @default.
• W2049202684 cites W1988146751 @default.
• W2049202684 cites W1989645409 @default.
• W2049202684 cites W1989672758 @default.
• W2049202684 cites W2002084676 @default.
• W2049202684 cites W2003078486 @default.
• W2049202684 cites W2015219393 @default.
• W2049202684 cites W2025653905 @default.
• W2049202684 cites W2026656818 @default.
• W2049202684 cites W2049857321 @default.
• W2049202684 cites W2058271794 @default.
• W2049202684 cites W2059837454 @default.
• W2049202684 cites W2079603968 @default.
• W2049202684 cites W2091233543 @default.
• W2049202684 cites W2097190406 @default.
• W2049202684 cites W2099283460 @default.
• W2049202684 cites W2100714230 @default.
• W2049202684 cites W2104714048 @default.
• W2049202684 cites W2106504576 @default.
• W2049202684 cites W2116119284 @default.
• W2049202684 cites W2137983211 @default.
• W2049202684 cites W2147461252 @default.
• W2049202684 cites W2150593711 @default.
• W2049202684 cites W2150781240 @default.
• W2049202684 cites W2150884987 @default.
• W2049202684 cites W2152907901 @default.
• W2049202684 cites W2154228396 @default.
• W2049202684 cites W2155399784 @default.
• W2049202684 cites W2165758113 @default.
• W2049202684 cites W2171277043 @default.
• W2049202684 doi "https://doi.org/10.1016/j.neucom.2008.10.014" @default.
• W2049202684 hasPublicationYear "2009" @default.
• W2049202684 type Work @default.
• W2049202684 sameAs 2049202684 @default.
• W2049202684 citedByCount "16" @default.
• W2049202684 countsByYear W20492026842012 @default.
• W2049202684 countsByYear W20492026842015 @default.
• W2049202684 countsByYear W20492026842017 @default.
• W2049202684 countsByYear W20492026842018 @default.
• W2049202684 countsByYear W20492026842019 @default.
• W2049202684 countsByYear W20492026842020 @default.
• W2049202684 countsByYear W20492026842021 @default.
• W2049202684 crossrefType "journal-article" @default.
• W2049202684 hasAuthorship W2049202684A5003799782 @default.
• W2049202684 hasAuthorship W2049202684A5019498183 @default.
• W2049202684 hasAuthorship W2049202684A5040911847 @default.
• W2049202684 hasAuthorship W2049202684A5057031606 @default.
• W2049202684 hasConcept C119857082 @default.
• W2049202684 hasConcept C153180895 @default.
• W2049202684 hasConcept C154945302 @default.
• W2049202684 hasConcept C19071747 @default.
• W2049202684 hasConcept C41008148 @default.
• W2049202684 hasConcept C50644808 @default.
• W2049202684 hasConcept C60908668 @default.
• W2049202684 hasConceptScore W2049202684C119857082 @default.
• W2049202684 hasConceptScore W2049202684C153180895 @default.
• W2049202684 hasConceptScore W2049202684C154945302 @default.
• W2049202684 hasConceptScore W2049202684C19071747 @default.
• W2049202684 hasConceptScore W2049202684C41008148 @default.
• W2049202684 hasConceptScore W2049202684C50644808 @default.
• W2049202684 hasConceptScore W2049202684C60908668 @default.
• W2049202684 hasIssue "10-12" @default.
• W2049202684 hasLocation W20492026841 @default.
• W2049202684 hasOpenAccess W2049202684 @default.
• W2049202684 hasPrimaryLocation W20492026841 @default.
• W2049202684 hasRelatedWork W1501213224 @default.
• W2049202684 hasRelatedWork W2184870701 @default.
• W2049202684 hasRelatedWork W2783038087 @default.
• W2049202684 hasRelatedWork W3106494386 @default.
• W2049202684 hasRelatedWork W3185179407 @default.
• W2049202684 hasRelatedWork W4206558754 @default.
• W2049202684 hasRelatedWork W4220975826 @default.
• W2049202684 hasRelatedWork W4245248941 @default.
• W2049202684 hasRelatedWork W4280611221 @default.
• W2049202684 hasRelatedWork W1629725936 @default.
• W2049202684 hasVolume "72" @default.
• W2049202684 isParatext "false" @default.
• W2049202684 isRetracted "false" @default.
• W2049202684 magId "2049202684" @default.
• W2049202684 workType "article" @default.