Matches in SemOpenAlex for { <https://semopenalex.org/work/W2021685588> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2021685588 abstract "The use of neurocomputing to solve real world problems is some times penalized by the long computing time, especially in the training phase of the neural network. A lot of approaches were suggested in the literature that allows to reduce the computing time and to enhance the generalization factor. The approach we propose in this paper is original by the fact that it is based on the following paradigm: Divide To Simplify or DTS. The task of learning is decomposed in 2 steps. In the first step, we analyze the set of the input patterns and decompose the input space in several regions of interest. This is done by using an unsupervised prototype based neural network: a Kohonen Self Organized feature Map (SOM). The second step consists of training several feature based networks to learn the behavior of each region of interest. In this way, we obtain a set of specialized neural networks. We will present in this paper various data driven methods that use the DTS paradigm to build efficient Multi- Neural Networks systems. The efficiency of this context means fast learning time, fast execution or relaxation time, enhanced generalization factor and intrinsic implementation on a parallel machine. Our approach has been used, with success, in an industrial real world process control to analyze such a complex problem with multi-variable data." @default.
- W2021685588 created "2016-06-24" @default.
- W2021685588 creator A5033864725 @default.
- W2021685588 creator A5050433560 @default.
- W2021685588 creator A5074887428 @default.
- W2021685588 date "1997-04-04" @default.
- W2021685588 modified "2023-10-01" @default.
- W2021685588 title "<title>Various ways for building a multi-neural network system: application to a control process</title>" @default.
- W2021685588 doi "https://doi.org/10.1117/12.271475" @default.
- W2021685588 hasPublicationYear "1997" @default.
- W2021685588 type Work @default.
- W2021685588 sameAs 2021685588 @default.
- W2021685588 citedByCount "1" @default.
- W2021685588 crossrefType "proceedings-article" @default.
- W2021685588 hasAuthorship W2021685588A5033864725 @default.
- W2021685588 hasAuthorship W2021685588A5050433560 @default.
- W2021685588 hasAuthorship W2021685588A5074887428 @default.
- W2021685588 hasConcept C111168008 @default.
- W2021685588 hasConcept C111919701 @default.
- W2021685588 hasConcept C119857082 @default.
- W2021685588 hasConcept C134306372 @default.
- W2021685588 hasConcept C138885662 @default.
- W2021685588 hasConcept C151730666 @default.
- W2021685588 hasConcept C154945302 @default.
- W2021685588 hasConcept C162324750 @default.
- W2021685588 hasConcept C177148314 @default.
- W2021685588 hasConcept C177264268 @default.
- W2021685588 hasConcept C187736073 @default.
- W2021685588 hasConcept C199360897 @default.
- W2021685588 hasConcept C2776401178 @default.
- W2021685588 hasConcept C2779343474 @default.
- W2021685588 hasConcept C2780451532 @default.
- W2021685588 hasConcept C33923547 @default.
- W2021685588 hasConcept C41008148 @default.
- W2021685588 hasConcept C41895202 @default.
- W2021685588 hasConcept C50644808 @default.
- W2021685588 hasConcept C86803240 @default.
- W2021685588 hasConcept C98045186 @default.
- W2021685588 hasConceptScore W2021685588C111168008 @default.
- W2021685588 hasConceptScore W2021685588C111919701 @default.
- W2021685588 hasConceptScore W2021685588C119857082 @default.
- W2021685588 hasConceptScore W2021685588C134306372 @default.
- W2021685588 hasConceptScore W2021685588C138885662 @default.
- W2021685588 hasConceptScore W2021685588C151730666 @default.
- W2021685588 hasConceptScore W2021685588C154945302 @default.
- W2021685588 hasConceptScore W2021685588C162324750 @default.
- W2021685588 hasConceptScore W2021685588C177148314 @default.
- W2021685588 hasConceptScore W2021685588C177264268 @default.
- W2021685588 hasConceptScore W2021685588C187736073 @default.
- W2021685588 hasConceptScore W2021685588C199360897 @default.
- W2021685588 hasConceptScore W2021685588C2776401178 @default.
- W2021685588 hasConceptScore W2021685588C2779343474 @default.
- W2021685588 hasConceptScore W2021685588C2780451532 @default.
- W2021685588 hasConceptScore W2021685588C33923547 @default.
- W2021685588 hasConceptScore W2021685588C41008148 @default.
- W2021685588 hasConceptScore W2021685588C41895202 @default.
- W2021685588 hasConceptScore W2021685588C50644808 @default.
- W2021685588 hasConceptScore W2021685588C86803240 @default.
- W2021685588 hasConceptScore W2021685588C98045186 @default.
- W2021685588 hasLocation W20216855881 @default.
- W2021685588 hasOpenAccess W2021685588 @default.
- W2021685588 hasPrimaryLocation W20216855881 @default.
- W2021685588 hasRelatedWork W1507623373 @default.
- W2021685588 hasRelatedWork W1509467138 @default.
- W2021685588 hasRelatedWork W1964738998 @default.
- W2021685588 hasRelatedWork W2093979523 @default.
- W2021685588 hasRelatedWork W2365088826 @default.
- W2021685588 hasRelatedWork W2800101833 @default.
- W2021685588 hasRelatedWork W2989932438 @default.
- W2021685588 hasRelatedWork W3201070945 @default.
- W2021685588 hasRelatedWork W60476941 @default.
- W2021685588 hasRelatedWork W1629725936 @default.
- W2021685588 isParatext "false" @default.
- W2021685588 isRetracted "false" @default.
- W2021685588 magId "2021685588" @default.
- W2021685588 workType "article" @default.