A quantitative uncertainty metric controls error in neural network-driven chemical discovery-Reference-Cited by-同舟云学术

A quantitative uncertainty metric controls error in neural network-driven chemical discovery

Published:2019 Issue:34 Volume:10 Page:7913-7922
ISSN:2041-6520
Container-title:Chemical Science
language:en
Short-container-title:Chem. Sci.

Author:

Janet Jon Paul¹²³⁴^ORCID,Duan Chenru¹²³⁴⁵^ORCID,Yang Tzuhsiung¹²³⁴,Nandy Aditya¹²³⁴⁵^ORCID,Kulik Heather J.¹²³⁴^ORCID

Affiliation:

1. Department of Chemical Engineering

2. Massachusetts Institute of Technology

3. Cambridge

4. USA

5. Department of Chemistry

Abstract

A predictive approach for driving down machine learning model errors is introduced and demonstrated across discovery for inorganic and organic chemistry.

Funder

Office of Naval Research Global

Burroughs Wellcome Fund

American Association for the Advancement of Science

Defense Advanced Research Projects Agency

Publisher

Royal Society of Chemistry (RSC)

Subject

General Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2019/SC/C9SC02298H

Reference92 articles.

1. Predicting the Band Gaps of Inorganic Solids by Machine Learning

2. Comparing molecules and solids across structural and alchemical space

3. A general-purpose machine learning framework for predicting properties of inorganic materials

4. Accelerating materials property predictions using machine learning

5. Machine learning meets volcano plots: computational discovery of cross-coupling catalysts

Cited by 139 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Spatially Resolved Uncertainties for Machine Learning Potentials;Journal of Chemical Information and Modeling;2024-08-07

2. Uncertainty quantification by direct propagation of shallow ensembles;Machine Learning: Science and Technology;2024-07-05

3. The present state and challenges of active learning in drug discovery;Drug Discovery Today;2024-06

4. Active learning of ternary alloy structures and energies;npj Computational Materials;2024-05-30

5. Learning Design Rules for Catalysts Through Computational Chemistry and Machine Learning;Exploring Chemical Concepts Through Theory and Computation;2024-05-17