Stage-oe-small.jpg

Inproceedings123: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Nguyen |ErsterAutorVorname=Anna }} {{Publikation Author |Rank=2 |Author=Tobias Weller }} {{Publikation Author |…“)
 
 
(4 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt)
Zeile 16: Zeile 16:
 
}}
 
}}
 
{{Inproceedings
 
{{Inproceedings
|Referiert=Nein
+
|Referiert=Ja
 
|Title=Making Neural Networks FAIR
 
|Title=Making Neural Networks FAIR
 
|Year=2020
 
|Year=2020
 
|Month=November
 
|Month=November
|Booktitle=Knowledge Graphs and Semantic Web Second Iberoamerican Conference and First Indo-American Conference, KGSWC 2020, Mérida, Mexico, November 26–27, 2020, Proceedings
+
|Booktitle=Proceedings of the Knowledge Graphs and Semantic Web (KGSWC'20)
 
|Pages=29-44
 
|Pages=29-44
 
|Publisher=Springer
 
|Publisher=Springer
Zeile 30: Zeile 30:
 
|Abstract=Research on neural networks has gained significant momentum over the past few years. Because training is a resource-intensive process and training data cannot always be made available to everyone, there has been a trend to reuse pre-trained neural networks. As such, neural networks themselves have become research data. In this paper, we first present the neural network ontology FAIRnets Ontology, an ontology to make existing neural network models findable, accessible, interoperable, and reusable according to the FAIR principles. Our ontology allows us to model neural networks on a meta-level in a structured way, including the representation of all network layers and their characteristics. Secondly, we have modeled over 18,400 neural networks from GitHub based on this ontology, which we provide to the public as a knowledge graph called FAIRnets, ready to be used for recommending suitable neural networks to data scientists.
 
|Abstract=Research on neural networks has gained significant momentum over the past few years. Because training is a resource-intensive process and training data cannot always be made available to everyone, there has been a trend to reuse pre-trained neural networks. As such, neural networks themselves have become research data. In this paper, we first present the neural network ontology FAIRnets Ontology, an ontology to make existing neural network models findable, accessible, interoperable, and reusable according to the FAIR principles. Our ontology allows us to model neural networks on a meta-level in a structured way, including the representation of all network layers and their characteristics. Secondly, we have modeled over 18,400 neural networks from GitHub based on this ontology, which we provide to the public as a knowledge graph called FAIRnets, ready to be used for recommending suitable neural networks to data scientists.
 
|ISBN=978-3-030-65383-5
 
|ISBN=978-3-030-65383-5
|Link=https://arxiv.org/abs/1907.11569
+
|Download=KGSWC_MakingNeuralNetworksFAIR_CameraReady.pdf
 +
|Link=https://link.springer.com/chapter/10.1007%2F978-3-030-65384-2_3
 +
|DOI Name=10.1007/978-3-030-65384-2_3
 
|Forschungsgruppe=Web Science
 
|Forschungsgruppe=Web Science
 
}}
 
}}
Zeile 38: Zeile 40:
 
{{Forschungsgebiet Auswahl
 
{{Forschungsgebiet Auswahl
 
|Forschungsgebiet=Künstliche Intelligenz
 
|Forschungsgebiet=Künstliche Intelligenz
 +
}}
 +
{{Forschungsgebiet Auswahl
 +
|Forschungsgebiet=Maschinelles Lernen
 
}}
 
}}

Aktuelle Version vom 2. Februar 2021, 15:45 Uhr


Making Neural Networks FAIR


Making Neural Networks FAIR



Published: 2020 November
Herausgeber: Villazón-Terrazas et al.
Buchtitel: Proceedings of the Knowledge Graphs and Semantic Web (KGSWC'20)
Nummer: 1232
Reihe: Communications in Computer and Information Science
Seiten: 29-44
Verlag: Springer

Referierte Veröffentlichung

BibTeX

Kurzfassung
Research on neural networks has gained significant momentum over the past few years. Because training is a resource-intensive process and training data cannot always be made available to everyone, there has been a trend to reuse pre-trained neural networks. As such, neural networks themselves have become research data. In this paper, we first present the neural network ontology FAIRnets Ontology, an ontology to make existing neural network models findable, accessible, interoperable, and reusable according to the FAIR principles. Our ontology allows us to model neural networks on a meta-level in a structured way, including the representation of all network layers and their characteristics. Secondly, we have modeled over 18,400 neural networks from GitHub based on this ontology, which we provide to the public as a knowledge graph called FAIRnets, ready to be used for recommending suitable neural networks to data scientists.

ISBN: 978-3-030-65383-5
Download: Media:KGSWC_MakingNeuralNetworksFAIR_CameraReady.pdf
Weitere Informationen unter: Link
DOI Link: 10.1007/978-3-030-65384-2_3



Forschungsgruppe

Web Science


Forschungsgebiet

Maschinelles Lernen, Künstliche Intelligenz, Semantic Web