Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382023404> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4382023404 endingPage "500" @default.
- W4382023404 startingPage "500" @default.
- W4382023404 abstract "Machine learning is a branch of artificial intelligence that dates back more than 50 years. It is currently experiencing a boom in research and technological development. With the rise of machine learning, the need to propose improved optimizers has become more acute, leading to the search for new gradient-based optimizers. In this paper, the ancient concept of fractional derivatives has been applied to some optimizers available in PyTorch. A comparative study is presented to show how the fractional versions of gradient optimizers could improve their performance on generative adversarial networks (GAN) and natural language applications with Bidirectional Encoder Representations from Transformers (BERT). The results are encouraging for both state-of-the art algorithms, GAN and BERT, and open up the possibility of exploring further applications of fractional calculus in machine learning." @default.
- W4382023404 created "2023-06-27" @default.
- W4382023404 creator A5055756907 @default.
- W4382023404 creator A5092263062 @default.
- W4382023404 date "2023-06-23" @default.
- W4382023404 modified "2023-09-30" @default.
- W4382023404 title "Fractional Gradient Optimizers for PyTorch: Enhancing GAN and BERT" @default.
- W4382023404 cites W1499749050 @default.
- W4382023404 cites W1984796440 @default.
- W4382023404 cites W1994616650 @default.
- W4382023404 cites W2007339694 @default.
- W4382023404 cites W2064675550 @default.
- W4382023404 cites W2589174422 @default.
- W4382023404 cites W2743957772 @default.
- W4382023404 cites W2810722694 @default.
- W4382023404 cites W2944712254 @default.
- W4382023404 cites W2969381807 @default.
- W4382023404 cites W3133118566 @default.
- W4382023404 cites W4296097265 @default.
- W4382023404 cites W4318484896 @default.
- W4382023404 cites W4366495605 @default.
- W4382023404 doi "https://doi.org/10.3390/fractalfract7070500" @default.
- W4382023404 hasPublicationYear "2023" @default.
- W4382023404 type Work @default.
- W4382023404 citedByCount "0" @default.
- W4382023404 crossrefType "journal-article" @default.
- W4382023404 hasAuthorship W4382023404A5055756907 @default.
- W4382023404 hasAuthorship W4382023404A5092263062 @default.
- W4382023404 hasBestOaLocation W43820234041 @default.
- W4382023404 hasConcept C108583219 @default.
- W4382023404 hasConcept C111919701 @default.
- W4382023404 hasConcept C118505674 @default.
- W4382023404 hasConcept C119599485 @default.
- W4382023404 hasConcept C119857082 @default.
- W4382023404 hasConcept C127413603 @default.
- W4382023404 hasConcept C154945302 @default.
- W4382023404 hasConcept C165801399 @default.
- W4382023404 hasConcept C2988773926 @default.
- W4382023404 hasConcept C39890363 @default.
- W4382023404 hasConcept C41008148 @default.
- W4382023404 hasConcept C66322947 @default.
- W4382023404 hasConceptScore W4382023404C108583219 @default.
- W4382023404 hasConceptScore W4382023404C111919701 @default.
- W4382023404 hasConceptScore W4382023404C118505674 @default.
- W4382023404 hasConceptScore W4382023404C119599485 @default.
- W4382023404 hasConceptScore W4382023404C119857082 @default.
- W4382023404 hasConceptScore W4382023404C127413603 @default.
- W4382023404 hasConceptScore W4382023404C154945302 @default.
- W4382023404 hasConceptScore W4382023404C165801399 @default.
- W4382023404 hasConceptScore W4382023404C2988773926 @default.
- W4382023404 hasConceptScore W4382023404C39890363 @default.
- W4382023404 hasConceptScore W4382023404C41008148 @default.
- W4382023404 hasConceptScore W4382023404C66322947 @default.
- W4382023404 hasIssue "7" @default.
- W4382023404 hasLocation W43820234041 @default.
- W4382023404 hasLocation W43820234042 @default.
- W4382023404 hasOpenAccess W4382023404 @default.
- W4382023404 hasPrimaryLocation W43820234041 @default.
- W4382023404 hasRelatedWork W2795261237 @default.
- W4382023404 hasRelatedWork W3014300295 @default.
- W4382023404 hasRelatedWork W3164822677 @default.
- W4382023404 hasRelatedWork W4223943233 @default.
- W4382023404 hasRelatedWork W4225161397 @default.
- W4382023404 hasRelatedWork W4312200629 @default.
- W4382023404 hasRelatedWork W4360585206 @default.
- W4382023404 hasRelatedWork W4364306694 @default.
- W4382023404 hasRelatedWork W4380075502 @default.
- W4382023404 hasRelatedWork W4380086463 @default.
- W4382023404 hasVolume "7" @default.
- W4382023404 isParatext "false" @default.
- W4382023404 isRetracted "false" @default.
- W4382023404 workType "article" @default.