Machine learning for molecular and materials science
File(s)Revised_Manuscript_V6_Resub.pdf (1.56 MB)
Accepted version
Author(s)
Butler, Keith
Davies, Daniel
Hugh, Cartwright
Isayev, Olexandr
Walsh, A
Type
Journal Article
Abstract
In this P
erspective, we outline the
progress and
potential of machine learning for
the
physical science
s
. We envisage a future where the design, synthesis, characterisation, and
application of
molecules and
material
s
is accelerated by artificial intelligence.
erspective, we outline the
progress and
potential of machine learning for
the
physical science
s
. We envisage a future where the design, synthesis, characterisation, and
application of
molecules and
material
s
is accelerated by artificial intelligence.
Date Issued
2018-07-26
Date Acceptance
2018-04-24
Citation
Nature, 2018, 559 (7715), pp.547-555
ISSN
0028-0836
Publisher
Nature Publishing Group
Start Page
547
End Page
555
Journal / Book Title
Nature
Volume
559
Issue
7715
Copyright Statement
© 2018 Springer Nature Limited. All rights reserved.
Sponsor
The Royal Society
The Leverhulme Trust
Grant Number
UF150657
PLP-2016-090
Subjects
Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
COMPUTATIONAL MATERIALS DESIGN
NEURAL-NETWORKS
DISCOVERY
COMPUTER
CHEMISTRY
MD Multidisciplinary
General Science & Technology
Publication Status
Published
Date Publish Online
2018-07-25