Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Felix A. Faber"'
Autor:
Emma King-Smith, Felix A. Faber, Usa Reilly, Anton V. Sinitskiy, Qingyi Yang, Bo Liu, Dennis Hyek, Alpha A. Lee
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract Structural diversification of lead molecules is a key component of drug discovery to explore chemical space. Late-stage functionalizations (LSFs) are versatile methodologies capable of installing functional handles on richly decorated interm
Externí odkaz:
https://doaj.org/article/f479aef07e3646c6b4b15365b07e1162
Publikováno v:
The Journal of chemical physics. 157(21)
Conventional kernel-based machine learning models for ab initio potential energy surfaces, while accurate and convenient in small data regimes, suffer immense computational cost as training set sizes increase. We introduce QML-Lightning, a PyTorch pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::010e6fcb066da49e87d3245321fcba1d
https://pubmed.ncbi.nlm.nih.gov/36511559
https://pubmed.ncbi.nlm.nih.gov/36511559
Publikováno v:
Materials Informatics. :171-179
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa25b1d98fffb92108820603c4a656bf
https://doi.org/10.1002/9783527802265.ch6
https://doi.org/10.1002/9783527802265.ch6
An assessment of the structural resolution of various fingerprints commonly used in machine learning
Autor:
Jörg Behler, Sandip De, Emir Kocer, Anatole von Lilienfeld, Stefan Goedecker, Anders S. Christensen, Deb Sankar De, Felix A. Faber, Behnam Parsaeifard
Atomic environment fingerprints are widely used in computational materials science, from machine learning potentials to the quantification of similarities between atomic configurations. Many approaches to the construction of such fingerprints, also c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2716e6d63de761d5db78de409181f0d9
Publikováno v:
Machine Learning Meets Quantum Physics ISBN: 9783030402440
The choice of how to represent a chemical compound has a considerable effect on the performance of quantum machine learning (QML) models based on kernel ridge regression (KRR). A carefully constructed representation can lower the prediction error for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20686bda6b2cd8ea56a34498466c63f7
https://doi.org/10.1007/978-3-030-40245-7_8
https://doi.org/10.1007/978-3-030-40245-7_8
Publikováno v:
Christensen, A S, Bratholm, L A, Faber, F A & Anatole Von Lilienfeld, O 2020, ' FCHL revisited : Faster and more accurate quantum machine learning ', Journal of Chemical Physics, vol. 152, no. 4, 044107 (2020) . https://doi.org/10.1063/1.5126701
We introduce the FCHL19 representation for atomic environments in molecules or condensed-phase systems. Machine learning models based on FCHL19 are able to yield predictions of atomic forces and energies of query compounds with chemical accuracy on t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c8921423f7a780979f8d2cde2aa3391
http://arxiv.org/abs/1909.01946
http://arxiv.org/abs/1909.01946
Autor:
Philipp Marquetand, Julia Westermayr, Felix A. Faber, O. Anatole von Lilienfeld, Anders S. Christensen
Publikováno v:
Machine Learning: Science and Technology. 1:025009
Excited-state dynamics simulations are a powerful tool to investigate photo-induced reactions of molecules and materials and provide complementary information to experiments. Since the applicability of these simulation techniques is limited by the co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1a8ebfc254aaea91e276adaac9ff07b
https://doi.org/10.1088/2632-2153/ab88d0
https://doi.org/10.1088/2632-2153/ab88d0
Publikováno v:
The Journal of chemical physics. 148(24)
We introduce a representation of any atom in any chemical environment for the automatized generation of universal kernel ridge regression-based quantum machine learning (QML) models of electronic properties, trained throughout chemical compound space
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be970d827094f9120788977372815c0f
https://pubmed.ncbi.nlm.nih.gov/29960351
https://pubmed.ncbi.nlm.nih.gov/29960351
Autor:
Luke Hutchison, Oriol Vinyals, Felix A. Faber, Steven Kearnes, George E. Dahl, Patrick Riley, Justin Gilmer, O. Anatole von Lilienfeld, Samuel S. Schoenholz, Bing Huang
Publikováno v:
Journal of chemical theory and computation. 13(11)
We investigate the impact of choosing regressors and molecular representations for the construction of fast machine learning (ML) models of 13 electronic ground-state properties of organic molecules. The performance of each regressor/representation/p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca6d5c641fd6ee5ec018c67122a7a29a
https://pubmed.ncbi.nlm.nih.gov/28926232
https://pubmed.ncbi.nlm.nih.gov/28926232
Publikováno v:
The Journal of Chemical Physics. 150:064105
The role of response operators is well established in quantum mechanics. We investigate their use for universal quantum machine learning models of response properties in molecules. After introducing a theoretical basis, we present and discuss numeric
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca39c34eb0a79d528041d3939498a4f9
https://doi.org/10.1063/1.5053562
https://doi.org/10.1063/1.5053562