Skip to main content Accessibility help
×
Home
Hostname: page-component-544b6db54f-5rlvm Total loading time: 0.145 Render date: 2021-10-22T23:53:36.864Z Has data issue: true Feature Flags: { "shouldUseShareProductTool": true, "shouldUseHypothesis": true, "isUnsiloEnabled": true, "metricsAbstractViews": false, "figures": true, "newCiteModal": false, "newCitedByModal": true, "newEcommerce": true, "newUsageEvents": true }

Neural Networks for Computational Chemistry: Pitfalls and Recommendations

Published online by Cambridge University Press:  21 February 2013

Grégoire Montavon
Affiliation:
Machine Learning Group, TU Berlin, Marchstraße 23, 10587 Berlin, Germany
Klaus-Robert Müller
Affiliation:
Machine Learning Group, TU Berlin, Marchstraße 23, 10587 Berlin, Germany Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 136-713, South Korea
Get access

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.

Type
Articles
Copyright
Copyright © Materials Research Society 2013

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Lorenz, Sönke, Groß, Axel, and Scheffler, Matthias. Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networks. Chemical Physics Letters, 395(4–6):210215, 2004.CrossRefGoogle Scholar
Manzhos, Sergei and Carrington, Tucker. A random-sampling high dimensional model representation neural network for building potential energy surfaces. J. Chem. Phys., 125:084109, 2006.10.1063/1.2336223CrossRefGoogle ScholarPubMed
Behler, Jörg. Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations. Physical Chemistry Chemical Physics, 13(40):1793017955, 2011.10.1039/c1cp21668fCrossRefGoogle ScholarPubMed
Snyder, John C., Rupp, Matthias, Hansen, Katja, Müller, Klaus-Robert, and Burke, Kieron. Finding Density Functionals with Machine Learning, Physical Review Letters, 108(25): 253002, American Physical Society, 2012.CrossRefGoogle ScholarPubMed
Rupp, Matthias, Tkatchenko, Alexandre, Müller, Klaus-Robert, and Anatole von Lilienfeld, O.. Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning, Physical Review Letters, 108(5):058301, 2012.10.1103/PhysRevLett.108.058301CrossRefGoogle ScholarPubMed
Montavon, Grégoire, Hansen, Katja, Fazli, Siamac, Rupp, Matthias, Biegler, Franziska, Ziehe, Andreas, Tkatchenko, Alexandre, Anatole von Lilienfeld, O., and Müller, Klaus-Robert. Learning Invariant Representations of Molecules for Atomization Energy Prediction, Advances in Neural Information Processing Systems 25, 449457, 2012.Google Scholar
Rumelhart, David E., Hinton, Geoffrey E., and Williams, Ronald J.. Learning representations by backpropagating errors, Nature, 323, 533536, 1986.10.1038/323533a0CrossRefGoogle Scholar
Bottou, Léon. Stochastic Gradient Learning in Neural Networks, Proceedings of Neuro-Nîmes 91, EC2, Nimes, France, 1991.Google Scholar
LeCun, Yann, Bottou, Léon, Orr, Geneviève B., and Müller, Klaus-Robert. Efficient BackProp, in Orr, G. B., and Müller, K-R. (Eds), Neural Networks: Tricks of the trade, Springer, 1998.Google Scholar
Montavon, Grégoire, Orr, Geneviève B., and Müller, Klaus-Robert (Eds). Neural Networks: Tricks of the Trade. 2nd edn, LNCS 7700, Springer, 2012.10.1007/978-3-642-35289-8CrossRefGoogle Scholar
Montavon, Grégoire, Braun, Mikio L., and Müller, Klaus-Robert. Kernel analysis of deep networks. Journal of Machine Learning Research, 12:25632581, 2011.Google Scholar
Blum, Lorenz C. and Reymond, Jean-Louis. 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. Journal of the American Chemical Society, 131(25):87328733, 2009.10.1021/ja902302hCrossRefGoogle ScholarPubMed
Rupp, Matthias, Tkatchenko, Alexandre, Müller, Klaus-Robert, and Anatole von Lilienfeld, O.. Reply to Comment by J.E. Moussa (Physical Review Letters 109(5): 059801, 2012), Physical Review Letters, 109(5): 059802, American Physical Society, 2012.10.1103/PhysRevLett.109.059802CrossRef

Send article to Kindle

To send this article to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about sending to your Kindle. Find out more about sending to your Kindle.

Note you can select to send to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be sent to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Neural Networks for Computational Chemistry: Pitfalls and Recommendations
Available formats
×

Send article to Dropbox

To send this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Dropbox.

Neural Networks for Computational Chemistry: Pitfalls and Recommendations
Available formats
×

Send article to Google Drive

To send this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Google Drive.

Neural Networks for Computational Chemistry: Pitfalls and Recommendations
Available formats
×
×

Reply to: Submit a response

Please enter your response.

Your details

Please enter a valid email address.

Conflicting interests

Do you have any conflicting interests? *