Matches in SemOpenAlex for { <https://semopenalex.org/work/W1547062801> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1547062801 abstract "The authors discuss the application of gradient methods (steepest descent and conjugate gradients) to an unsupervised neural network that uses potential functions in the output layer as previously reported by the authors (1990). The nature of most unsupervised neural networks makes the gradient step algorithm the only possible way to optimize the network's function. The network reported by the authors in 1990 can make use of other gradient methods. Experiments with the steepest descent/ascent and conjugate gradients algorithms show a potential decrease in the number of iterations. The contours of the network's function showed considerable variation, especially close to the local optima. This nature restricted the line search algorithms that could be used. Simulations confirm this fact by showing how a crude line search algorithm performs better than a semiexact line search algorithm. >" @default.
- W1547062801 created "2016-06-24" @default.
- W1547062801 creator A5026237897 @default.
- W1547062801 creator A5036796702 @default.
- W1547062801 creator A5039318050 @default.
- W1547062801 date "2002-12-09" @default.
- W1547062801 modified "2023-09-24" @default.
- W1547062801 title "Gradient methods in unsupervised neural networks" @default.
- W1547062801 cites W11974643 @default.
- W1547062801 cites W1490454746 @default.
- W1547062801 cites W1990863955 @default.
- W1547062801 cites W1991848143 @default.
- W1547062801 cites W2014702547 @default.
- W1547062801 cites W2025211319 @default.
- W1547062801 cites W2068470708 @default.
- W1547062801 cites W2094480958 @default.
- W1547062801 doi "https://doi.org/10.1109/ijcnn.1991.170685" @default.
- W1547062801 hasPublicationYear "2002" @default.
- W1547062801 type Work @default.
- W1547062801 sameAs 1547062801 @default.
- W1547062801 citedByCount "0" @default.
- W1547062801 crossrefType "proceedings-article" @default.
- W1547062801 hasAuthorship W1547062801A5026237897 @default.
- W1547062801 hasAuthorship W1547062801A5036796702 @default.
- W1547062801 hasAuthorship W1547062801A5039318050 @default.
- W1547062801 hasConcept C11413529 @default.
- W1547062801 hasConcept C115680565 @default.
- W1547062801 hasConcept C126255220 @default.
- W1547062801 hasConcept C14036430 @default.
- W1547062801 hasConcept C153180895 @default.
- W1547062801 hasConcept C153258448 @default.
- W1547062801 hasConcept C154945302 @default.
- W1547062801 hasConcept C155032097 @default.
- W1547062801 hasConcept C178635117 @default.
- W1547062801 hasConcept C198352243 @default.
- W1547062801 hasConcept C2524010 @default.
- W1547062801 hasConcept C26362088 @default.
- W1547062801 hasConcept C33923547 @default.
- W1547062801 hasConcept C38652104 @default.
- W1547062801 hasConcept C41008148 @default.
- W1547062801 hasConcept C50644808 @default.
- W1547062801 hasConcept C78458016 @default.
- W1547062801 hasConcept C81184566 @default.
- W1547062801 hasConcept C85522705 @default.
- W1547062801 hasConcept C86803240 @default.
- W1547062801 hasConceptScore W1547062801C11413529 @default.
- W1547062801 hasConceptScore W1547062801C115680565 @default.
- W1547062801 hasConceptScore W1547062801C126255220 @default.
- W1547062801 hasConceptScore W1547062801C14036430 @default.
- W1547062801 hasConceptScore W1547062801C153180895 @default.
- W1547062801 hasConceptScore W1547062801C153258448 @default.
- W1547062801 hasConceptScore W1547062801C154945302 @default.
- W1547062801 hasConceptScore W1547062801C155032097 @default.
- W1547062801 hasConceptScore W1547062801C178635117 @default.
- W1547062801 hasConceptScore W1547062801C198352243 @default.
- W1547062801 hasConceptScore W1547062801C2524010 @default.
- W1547062801 hasConceptScore W1547062801C26362088 @default.
- W1547062801 hasConceptScore W1547062801C33923547 @default.
- W1547062801 hasConceptScore W1547062801C38652104 @default.
- W1547062801 hasConceptScore W1547062801C41008148 @default.
- W1547062801 hasConceptScore W1547062801C50644808 @default.
- W1547062801 hasConceptScore W1547062801C78458016 @default.
- W1547062801 hasConceptScore W1547062801C81184566 @default.
- W1547062801 hasConceptScore W1547062801C85522705 @default.
- W1547062801 hasConceptScore W1547062801C86803240 @default.
- W1547062801 hasLocation W15470628011 @default.
- W1547062801 hasOpenAccess W1547062801 @default.
- W1547062801 hasPrimaryLocation W15470628011 @default.
- W1547062801 hasRelatedWork W1518218943 @default.
- W1547062801 hasRelatedWork W1994309896 @default.
- W1547062801 hasRelatedWork W2143672845 @default.
- W1547062801 hasRelatedWork W2405196115 @default.
- W1547062801 hasRelatedWork W2737082271 @default.
- W1547062801 hasRelatedWork W2785921341 @default.
- W1547062801 hasRelatedWork W2786746258 @default.
- W1547062801 hasRelatedWork W2905519666 @default.
- W1547062801 hasRelatedWork W2982582399 @default.
- W1547062801 hasRelatedWork W3008847659 @default.
- W1547062801 hasRelatedWork W3017865777 @default.
- W1547062801 hasRelatedWork W3021406765 @default.
- W1547062801 hasRelatedWork W3034547948 @default.
- W1547062801 hasRelatedWork W3081401713 @default.
- W1547062801 hasRelatedWork W3093504610 @default.
- W1547062801 hasRelatedWork W3097919408 @default.
- W1547062801 hasRelatedWork W3203740280 @default.
- W1547062801 hasRelatedWork W2341716949 @default.
- W1547062801 hasRelatedWork W2959967000 @default.
- W1547062801 hasRelatedWork W3111327560 @default.
- W1547062801 isParatext "false" @default.
- W1547062801 isRetracted "false" @default.
- W1547062801 magId "1547062801" @default.
- W1547062801 workType "article" @default.