English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  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

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0002-B794-8 Version Permalink: https://hdl.handle.net/21.11116/0000-0004-C652-0
Genre: Conference Paper

Files

show Files
hide Files
:
1706.08566.pdf (Preprint), 10MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0003-CFE5-2
Name:
1706.08566.pdf
Description:
arXiv:1706.08566v5 [stat.ML] 19 Dec 2017
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
2018
Copyright Info:
-
License:
https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html

Locators

show

Creators

show
hide
 Creators:
Schütt, K. T.1, Author
Kindermans, P.-J.1, Author
Sauceda, Huziel E.2, Author           
Chmiela, S.1, Author
Tkatchenko, Alexandre3, Author
Müller, Klaus-Robert1, 4, 5, Author
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              

Content

show
hide
Free keywords: -
 Abstract: 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

show
hide
Language(s): eng - English
 Dates: 20172018
 Publication Status: Issued
 Pages: 11
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: URI: https://papers.nips.cc/paper/6700-schnet-a-continuous-filter-convolutional-neural-network-for-modeling-quantum-interactions
 Degree: -

Event

show
hide
Title: 31st Conference on Neural Information Processing Systems (NIPS 2017)
Place of Event: Long Beach, CA, USA
Start-/End Date: 2017-12-04 - 2017-12-09

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems
Source Genre: Proceedings
 Creator(s):
von Luxburg, Ulrike, Editor
Affiliations:
-
Publ. Info: La Jolla, CA : Neural Information Processing Systems (NIPS) Foundation
Pages: 7102 Volume / Issue: 30 Sequence Number: - Start / End Page: 992 - 1002 Identifier: ISBN: 978-1-5108-6096-4