Matches in SemOpenAlex for { <https://semopenalex.org/work/W2168013730> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2168013730 abstract "This paper shows the advantage of using neural network modularity over conventional learning schemes to approximate complex functions. Indeed, it is difficult for artificial neural networks like Kohonen extended maps to converge toward an efficient and adequate solution when the dimensionality of the input and output spaces are high. Associated to an appropriate learning technique, modularity in neural networks is able to overcome the high dimensionality of the input/input space by decomposing it into different intermediate spaces of reduced dimensionality. The decomposition results in independent neural modules. The efficiency of this learning technique will be enlightened with a visual servoing application. In this application, the relationship between the visual features issued from a stereoscopic vision system and the angles of a 5 DOF-robot will be learned and approximated. Simulations have been conducted and clearly show that this complex, nonlinear, and high dimensional function can be learned efficiently with the neural network modularity approach. Moreover, we show through these simulations that neural modules can be re-utilized, thus reducing the convergence time of the learning and the memory requirements." @default.
- W2168013730 created "2016-06-24" @default.
- W2168013730 creator A5024673701 @default.
- W2168013730 creator A5042099070 @default.
- W2168013730 creator A5047132129 @default.
- W2168013730 date "2006-01-01" @default.
- W2168013730 modified "2023-10-16" @default.
- W2168013730 title "Bi-directional Modularity to Learn Visual Servoing Tasks" @default.
- W2168013730 cites W140960986 @default.
- W2168013730 cites W1482149632 @default.
- W2168013730 cites W1602180906 @default.
- W2168013730 cites W1679913846 @default.
- W2168013730 cites W1970549371 @default.
- W2168013730 cites W1975318316 @default.
- W2168013730 cites W2041465020 @default.
- W2168013730 cites W2150884987 @default.
- W2168013730 cites W2159403624 @default.
- W2168013730 doi "https://doi.org/10.1109/ijcnn.2006.246794" @default.
- W2168013730 hasPublicationYear "2006" @default.
- W2168013730 type Work @default.
- W2168013730 sameAs 2168013730 @default.
- W2168013730 citedByCount "1" @default.
- W2168013730 crossrefType "proceedings-article" @default.
- W2168013730 hasAuthorship W2168013730A5024673701 @default.
- W2168013730 hasAuthorship W2168013730A5042099070 @default.
- W2168013730 hasAuthorship W2168013730A5047132129 @default.
- W2168013730 hasConcept C10912380 @default.
- W2168013730 hasConcept C111030470 @default.
- W2168013730 hasConcept C154945302 @default.
- W2168013730 hasConcept C162324750 @default.
- W2168013730 hasConcept C2777303404 @default.
- W2168013730 hasConcept C2779478453 @default.
- W2168013730 hasConcept C41008148 @default.
- W2168013730 hasConcept C50522688 @default.
- W2168013730 hasConcept C50644808 @default.
- W2168013730 hasConcept C54355233 @default.
- W2168013730 hasConcept C86803240 @default.
- W2168013730 hasConcept C90509273 @default.
- W2168013730 hasConceptScore W2168013730C10912380 @default.
- W2168013730 hasConceptScore W2168013730C111030470 @default.
- W2168013730 hasConceptScore W2168013730C154945302 @default.
- W2168013730 hasConceptScore W2168013730C162324750 @default.
- W2168013730 hasConceptScore W2168013730C2777303404 @default.
- W2168013730 hasConceptScore W2168013730C2779478453 @default.
- W2168013730 hasConceptScore W2168013730C41008148 @default.
- W2168013730 hasConceptScore W2168013730C50522688 @default.
- W2168013730 hasConceptScore W2168013730C50644808 @default.
- W2168013730 hasConceptScore W2168013730C54355233 @default.
- W2168013730 hasConceptScore W2168013730C86803240 @default.
- W2168013730 hasConceptScore W2168013730C90509273 @default.
- W2168013730 hasLocation W21680137301 @default.
- W2168013730 hasOpenAccess W2168013730 @default.
- W2168013730 hasPrimaryLocation W21680137301 @default.
- W2168013730 hasRelatedWork W1993377409 @default.
- W2168013730 hasRelatedWork W2082114066 @default.
- W2168013730 hasRelatedWork W2103779883 @default.
- W2168013730 hasRelatedWork W2118929088 @default.
- W2168013730 hasRelatedWork W2516826372 @default.
- W2168013730 hasRelatedWork W2775473286 @default.
- W2168013730 hasRelatedWork W286997960 @default.
- W2168013730 hasRelatedWork W4293869118 @default.
- W2168013730 hasRelatedWork W2107326529 @default.
- W2168013730 hasRelatedWork W2152244067 @default.
- W2168013730 isParatext "false" @default.
- W2168013730 isRetracted "false" @default.
- W2168013730 magId "2168013730" @default.
- W2168013730 workType "article" @default.