Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Schütt, K. T., Kindermans, P.-J., Sauceda, H. E., Chmiela, S., Tkatchenko, A., & Müller, K.-R. (2018). SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. In U. von Luxburg (Ed.), Advances in Neural Information Processing Systems (pp. 992-1002). La Jolla, CA: Neural Information Processing Systems (NIPS) Foundation. Retrieved from https://papers.nips.cc/paper/6700-schnet-a-continuous-filter-convolutional-neural-network-for-modeling-quantum-interactions.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0002-B794-8 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0004-C652-0
Genre: Konferenzbeitrag

Dateien

einblenden: Dateien
ausblenden: Dateien
:
1706.08566.pdf (Preprint), 10MB
Öffnen   Speichern
Datei-Permalink:
https://hdl.handle.net/21.11116/0000-0003-CFE5-2
Name:
1706.08566.pdf
Beschreibung:
arXiv:1706.08566v5 [stat.ML] 19 Dec 2017
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Öffnen
Copyright Datum:
2018
Copyright Info:
-
Lizenz:
https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Schütt, K. T.1, Autor
Kindermans, P.-J.1, Autor
Sauceda, Huziel E.2, Autor           
Chmiela, S.1, Autor
Tkatchenko, Alexandre3, Autor
Müller, Klaus-Robert1, 4, 5, Autor
Affiliations:
1Machine Learning Group, Technische Universität Berlin, Germany, ou_persistent22              
2Theory, Fritz Haber Institute, Max Planck Society, ou_634547              
3Physics and Materials Science Research Unit, University of Luxembourg, ou_persistent22              
4Max-Planck-Institut für Informatik, Saarbrücken, Germany, ou_persistent22              
5Dept. of Brain and Cognitive Engineering, Korea University, Seoul, South Korea, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not
restricted to a grid. Instead, their precise locations contain essential physical
information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-
chemical principles. Our architecture achieves state-of-the-art performance for
benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally,
we introduce a more challenging benchmark with chemical and structural variations
that suggests the path for further work.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20172018
 Publikationsstatus: Erschienen
 Seiten: 11
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: Expertenbegutachtung
 Identifikatoren: URI: https://papers.nips.cc/paper/6700-schnet-a-continuous-filter-convolutional-neural-network-for-modeling-quantum-interactions
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 31st Conference on Neural Information Processing Systems (NIPS 2017)
Veranstaltungsort: Long Beach, CA, USA
Start-/Enddatum: 2017-12-04 - 2017-12-09

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Advances in Neural Information Processing Systems
Genre der Quelle: Konferenzband
 Urheber:
von Luxburg, Ulrike, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: La Jolla, CA : Neural Information Processing Systems (NIPS) Foundation
Seiten: 7102 Band / Heft: 30 Artikelnummer: - Start- / Endseite: 992 - 1002 Identifikator: ISBN: 978-1-5108-6096-4