Neural networks for computational chemistry: Pitfalls and recommendations

Grégoire Montavon, Klaus Robert Müller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There is a long history of using neural networks for function approximation in computational physics and chemistry. Despite their conceptual simplicity, the practitioner may face difficulties when it comes to putting them to work. This small guide intends to pinpoint some neural networks pitfalls, along with corresponding solutions to successfully realize function approximation tasks in physics, chemistry or other fields.

Original languageEnglish
Title of host publicationMaterials Informatics
PublisherMaterials Research Society
Pages24-29
Number of pages6
ISBN (Print)9781632661135
DOIs
Publication statusPublished - 2013
Event2012 MRS Fall Meeting - Boston, MA, United States
Duration: 2012 Nov 252012 Nov 30

Publication series

NameMaterials Research Society Symposium Proceedings
Volume1523
ISSN (Print)0272-9172

Other

Other2012 MRS Fall Meeting
CountryUnited States
CityBoston, MA
Period12/11/2512/11/30

ASJC Scopus subject areas

  • Materials Science(all)
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Neural networks for computational chemistry: Pitfalls and recommendations'. Together they form a unique fingerprint.

  • Cite this

    Montavon, G., & Müller, K. R. (2013). Neural networks for computational chemistry: Pitfalls and recommendations. In Materials Informatics (pp. 24-29). (Materials Research Society Symposium Proceedings; Vol. 1523). Materials Research Society. https://doi.org/10.1557/opl.2013.189