Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895097035> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2895097035 endingPage "72" @default.
- W2895097035 startingPage "62" @default.
- W2895097035 abstract "We improve the training time of deep feedforward neural networks using a modified version of gradient descent we call Predictor-Corrector Gradient Descent (PCGD). PCGD uses predictor-corrector inspired techniques to enhance gradient descent. This method uses a sparse history of network parameter values to make periodic predictions of future parameter values in an effort to skip unnecessary training iterations. This method can cut the number of training epochs needed for a network to reach a particular testing accuracy by nearly one half when compared to stochastic gradient descent (SGD). PCGD can also outperform, with some trade-offs, Nesterov’s Accelerated Gradient (NAG)." @default.
- W2895097035 created "2018-10-12" @default.
- W2895097035 creator A5005336279 @default.
- W2895097035 creator A5044655940 @default.
- W2895097035 date "2018-01-01" @default.
- W2895097035 modified "2023-10-06" @default.
- W2895097035 title "Training Neural Networks Using Predictor-Corrector Gradient Descent" @default.
- W2895097035 cites W1603614877 @default.
- W2895097035 cites W1974680426 @default.
- W2895097035 cites W1988720110 @default.
- W2895097035 cites W2067102802 @default.
- W2895097035 cites W2100556411 @default.
- W2895097035 cites W2288286756 @default.
- W2895097035 cites W2465345967 @default.
- W2895097035 cites W2465999789 @default.
- W2895097035 cites W2586591890 @default.
- W2895097035 cites W280536263 @default.
- W2895097035 cites W2964139918 @default.
- W2895097035 doi "https://doi.org/10.1007/978-3-030-01424-7_7" @default.
- W2895097035 hasPublicationYear "2018" @default.
- W2895097035 type Work @default.
- W2895097035 sameAs 2895097035 @default.
- W2895097035 citedByCount "0" @default.
- W2895097035 crossrefType "book-chapter" @default.
- W2895097035 hasAuthorship W2895097035A5005336279 @default.
- W2895097035 hasAuthorship W2895097035A5044655940 @default.
- W2895097035 hasConcept C11413529 @default.
- W2895097035 hasConcept C115680565 @default.
- W2895097035 hasConcept C127413603 @default.
- W2895097035 hasConcept C133731056 @default.
- W2895097035 hasConcept C153258448 @default.
- W2895097035 hasConcept C154945302 @default.
- W2895097035 hasConcept C155032097 @default.
- W2895097035 hasConcept C206688291 @default.
- W2895097035 hasConcept C26362088 @default.
- W2895097035 hasConcept C38858127 @default.
- W2895097035 hasConcept C41008148 @default.
- W2895097035 hasConcept C47702885 @default.
- W2895097035 hasConcept C50644808 @default.
- W2895097035 hasConceptScore W2895097035C11413529 @default.
- W2895097035 hasConceptScore W2895097035C115680565 @default.
- W2895097035 hasConceptScore W2895097035C127413603 @default.
- W2895097035 hasConceptScore W2895097035C133731056 @default.
- W2895097035 hasConceptScore W2895097035C153258448 @default.
- W2895097035 hasConceptScore W2895097035C154945302 @default.
- W2895097035 hasConceptScore W2895097035C155032097 @default.
- W2895097035 hasConceptScore W2895097035C206688291 @default.
- W2895097035 hasConceptScore W2895097035C26362088 @default.
- W2895097035 hasConceptScore W2895097035C38858127 @default.
- W2895097035 hasConceptScore W2895097035C41008148 @default.
- W2895097035 hasConceptScore W2895097035C47702885 @default.
- W2895097035 hasConceptScore W2895097035C50644808 @default.
- W2895097035 hasLocation W28950970351 @default.
- W2895097035 hasOpenAccess W2895097035 @default.
- W2895097035 hasPrimaryLocation W28950970351 @default.
- W2895097035 hasRelatedWork W1532799615 @default.
- W2895097035 hasRelatedWork W1579649061 @default.
- W2895097035 hasRelatedWork W2041914054 @default.
- W2895097035 hasRelatedWork W2049463817 @default.
- W2895097035 hasRelatedWork W2128506797 @default.
- W2895097035 hasRelatedWork W2766636532 @default.
- W2895097035 hasRelatedWork W2785612459 @default.
- W2895097035 hasRelatedWork W2786746258 @default.
- W2895097035 hasRelatedWork W3007093918 @default.
- W2895097035 hasRelatedWork W3034547948 @default.
- W2895097035 hasRelatedWork W3045679877 @default.
- W2895097035 hasRelatedWork W305874333 @default.
- W2895097035 hasRelatedWork W3081401713 @default.
- W2895097035 hasRelatedWork W3091372384 @default.
- W2895097035 hasRelatedWork W3096443866 @default.
- W2895097035 hasRelatedWork W3131276897 @default.
- W2895097035 hasRelatedWork W3160167280 @default.
- W2895097035 hasRelatedWork W3203740280 @default.
- W2895097035 hasRelatedWork W2341716949 @default.
- W2895097035 hasRelatedWork W2959967000 @default.
- W2895097035 isParatext "false" @default.
- W2895097035 isRetracted "false" @default.
- W2895097035 magId "2895097035" @default.
- W2895097035 workType "book-chapter" @default.