Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897316208> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2897316208 abstract "The maximum entropy principle is a well established approach to unsupervised optimization. Entropy maximization learning algorithms for single-layered neural networks already exist for the cases in which the number of output neurons is greater or equal to the number of input neurons. These models were successfully employed in various applications, most notably for independent component analysis. In this work, we generalize the maximum entropy principle to a single-layered neural network with fewer output than input neurons. The proposed learning algorithm finds a low-dimensional representation of the data and identifies the independent components within it. In general, such a model must incorporate some prior knowledge of the input distribution; however, we overcome this difficulty using a variational approach. We illustrate the performance of the model through several examples and compare it to other algorithms. While our model achieves similar results to the state-of-the-art algorithm for overdetermined independent component analysis within a similar convergence time, its main advantage lies in its ability to be learned efficiently on-line." @default.
- W2897316208 created "2018-10-26" @default.
- W2897316208 creator A5009349156 @default.
- W2897316208 creator A5088640125 @default.
- W2897316208 date "2018-07-01" @default.
- W2897316208 modified "2023-09-23" @default.
- W2897316208 title "An Entropy Maximization Approach to Optimal Dimensionality Reduction" @default.
- W2897316208 cites W1970789124 @default.
- W2897316208 cites W1971027050 @default.
- W2897316208 cites W2032558547 @default.
- W2897316208 cites W2101185247 @default.
- W2897316208 cites W2105909330 @default.
- W2897316208 cites W2108384452 @default.
- W2897316208 cites W2122925692 @default.
- W2897316208 cites W2123806929 @default.
- W2897316208 cites W2128495200 @default.
- W2897316208 cites W2131329059 @default.
- W2897316208 cites W2133087656 @default.
- W2897316208 cites W2137234026 @default.
- W2897316208 cites W2140499889 @default.
- W2897316208 cites W2148989240 @default.
- W2897316208 cites W2170562615 @default.
- W2897316208 cites W2170934142 @default.
- W2897316208 cites W2273913668 @default.
- W2897316208 cites W2469673389 @default.
- W2897316208 cites W2593116425 @default.
- W2897316208 cites W2593634001 @default.
- W2897316208 cites W3099514962 @default.
- W2897316208 cites W92728042 @default.
- W2897316208 doi "https://doi.org/10.1109/ijcnn.2018.8489575" @default.
- W2897316208 hasPublicationYear "2018" @default.
- W2897316208 type Work @default.
- W2897316208 sameAs 2897316208 @default.
- W2897316208 citedByCount "0" @default.
- W2897316208 crossrefType "proceedings-article" @default.
- W2897316208 hasAuthorship W2897316208A5009349156 @default.
- W2897316208 hasAuthorship W2897316208A5088640125 @default.
- W2897316208 hasConcept C106301342 @default.
- W2897316208 hasConcept C111030470 @default.
- W2897316208 hasConcept C11413529 @default.
- W2897316208 hasConcept C121332964 @default.
- W2897316208 hasConcept C126255220 @default.
- W2897316208 hasConcept C127233936 @default.
- W2897316208 hasConcept C153180895 @default.
- W2897316208 hasConcept C154945302 @default.
- W2897316208 hasConcept C27438332 @default.
- W2897316208 hasConcept C2776330181 @default.
- W2897316208 hasConcept C28826006 @default.
- W2897316208 hasConcept C33923547 @default.
- W2897316208 hasConcept C41008148 @default.
- W2897316208 hasConcept C50644808 @default.
- W2897316208 hasConcept C62520636 @default.
- W2897316208 hasConcept C70518039 @default.
- W2897316208 hasConcept C81901731 @default.
- W2897316208 hasConcept C9679016 @default.
- W2897316208 hasConceptScore W2897316208C106301342 @default.
- W2897316208 hasConceptScore W2897316208C111030470 @default.
- W2897316208 hasConceptScore W2897316208C11413529 @default.
- W2897316208 hasConceptScore W2897316208C121332964 @default.
- W2897316208 hasConceptScore W2897316208C126255220 @default.
- W2897316208 hasConceptScore W2897316208C127233936 @default.
- W2897316208 hasConceptScore W2897316208C153180895 @default.
- W2897316208 hasConceptScore W2897316208C154945302 @default.
- W2897316208 hasConceptScore W2897316208C27438332 @default.
- W2897316208 hasConceptScore W2897316208C2776330181 @default.
- W2897316208 hasConceptScore W2897316208C28826006 @default.
- W2897316208 hasConceptScore W2897316208C33923547 @default.
- W2897316208 hasConceptScore W2897316208C41008148 @default.
- W2897316208 hasConceptScore W2897316208C50644808 @default.
- W2897316208 hasConceptScore W2897316208C62520636 @default.
- W2897316208 hasConceptScore W2897316208C70518039 @default.
- W2897316208 hasConceptScore W2897316208C81901731 @default.
- W2897316208 hasConceptScore W2897316208C9679016 @default.
- W2897316208 hasLocation W28973162081 @default.
- W2897316208 hasOpenAccess W2897316208 @default.
- W2897316208 hasPrimaryLocation W28973162081 @default.
- W2897316208 hasRelatedWork W2072405693 @default.
- W2897316208 hasRelatedWork W2095834362 @default.
- W2897316208 hasRelatedWork W2127183517 @default.
- W2897316208 hasRelatedWork W2172019219 @default.
- W2897316208 hasRelatedWork W2889755823 @default.
- W2897316208 hasRelatedWork W2897316208 @default.
- W2897316208 hasRelatedWork W3153525586 @default.
- W2897316208 hasRelatedWork W3204556447 @default.
- W2897316208 hasRelatedWork W3211035526 @default.
- W2897316208 hasRelatedWork W4244943737 @default.
- W2897316208 isParatext "false" @default.
- W2897316208 isRetracted "false" @default.
- W2897316208 magId "2897316208" @default.
- W2897316208 workType "article" @default.