FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384627417> ?p ?o ?g. }

• W4384627417 abstract "The feature vector mapping used to represent chemical systems is a key factor governing the superior data-efficiency of kernel based quantum machine learning (QML) models applicable throughout chemical compound space. Unfortunately, the most accurate representations require a high dimensional feature mapping, thereby imposing a considerable computational burden on model training and use. We introduce compact yet accurate, linear scaling QML representations based on atomic Gaussian many-body distribution functionals (MBDF), and their derivatives. Weighted density functions (DF) of MBDF values are used as global representations which are constant in size, i.e.~invariant with respect to the number of atoms. We report predictive performance and training data efficiency that is competitive with state of the art for two diverse datasets of organic molecules, QM9 and QMugs. Generalization capability has been investigated for atomization energies, HOMO-LUMO eigenvalues and gap, internal energies at 0 K, zero point vibrational energies, dipole moment norm, static isotropic polarizability, and heat capacity as encoded in QM9. MBDF based QM9 performance lowers the optimal Pareto front spanned between sampling and training cost to compute node minutes,~effectively sampling chemical compound space with chemical accuracy at a sampling rate of $sim 48$ molecules per core second." @default.
• W4384627417 created "2023-07-19" @default.
• W4384627417 creator A5024088138 @default.
• W4384627417 creator A5074882900 @default.
• W4384627417 creator A5088793872 @default.
• W4384627417 date "2023-07-18" @default.
• W4384627417 modified "2023-09-30" @default.
• W4384627417 title "Kernel based quantum machine learning at record rate: Many-body distribution functionals as compact representations" @default.
• W4384627417 cites W1531674615 @default.
• W4384627417 cites W1584846110 @default.
• W4384627417 cites W1865667476 @default.
• W4384627417 cites W1964882117 @default.
• W4384627417 cites W1975997599 @default.
• W4384627417 cites W1978183953 @default.
• W4384627417 cites W1981049088 @default.
• W4384627417 cites W1981745234 @default.
• W4384627417 cites W1988091937 @default.
• W4384627417 cites W2003301106 @default.
• W4384627417 cites W2020786104 @default.
• W4384627417 cites W2023271753 @default.
• W4384627417 cites W2025444507 @default.
• W4384627417 cites W2029413789 @default.
• W4384627417 cites W2033169180 @default.
• W4384627417 cites W2037761619 @default.
• W4384627417 cites W2037782625 @default.
• W4384627417 cites W2051434435 @default.
• W4384627417 cites W2063007245 @default.
• W4384627417 cites W2067050455 @default.
• W4384627417 cites W2080635178 @default.
• W4384627417 cites W2083415705 @default.
• W4384627417 cites W2084276247 @default.
• W4384627417 cites W2104489082 @default.
• W4384627417 cites W2105616783 @default.
• W4384627417 cites W2112850441 @default.
• W4384627417 cites W2118020555 @default.
• W4384627417 cites W2143981217 @default.
• W4384627417 cites W2153693853 @default.
• W4384627417 cites W2154455129 @default.
• W4384627417 cites W2164524421 @default.
• W4384627417 cites W2197007850 @default.
• W4384627417 cites W2337496963 @default.
• W4384627417 cites W2541404351 @default.
• W4384627417 cites W2585152223 @default.
• W4384627417 cites W26088913 @default.
• W4384627417 cites W2753962198 @default.
• W4384627417 cites W2768213699 @default.
• W4384627417 cites W2776192919 @default.
• W4384627417 cites W2792348590 @default.
• W4384627417 cites W2794704841 @default.
• W4384627417 cites W2891365537 @default.
• W4384627417 cites W2910857709 @default.
• W4384627417 cites W2911997094 @default.
• W4384627417 cites W2962872055 @default.
• W4384627417 cites W2976720228 @default.
• W4384627417 cites W3003486042 @default.
• W4384627417 cites W3003838176 @default.
• W4384627417 cites W3013487850 @default.
• W4384627417 cites W3035752258 @default.
• W4384627417 cites W3037603368 @default.
• W4384627417 cites W3037990336 @default.
• W4384627417 cites W3041909131 @default.
• W4384627417 cites W3043300003 @default.
• W4384627417 cites W3085090411 @default.
• W4384627417 cites W3088965305 @default.
• W4384627417 cites W3098544579 @default.
• W4384627417 cites W3099878876 @default.
• W4384627417 cites W3101744125 @default.
• W4384627417 cites W3102449990 @default.
• W4384627417 cites W3102659967 @default.
• W4384627417 cites W3103502300 @default.
• W4384627417 cites W3103971946 @default.
• W4384627417 cites W3106310231 @default.
• W4384627417 cites W3158948853 @default.
• W4384627417 cites W3185227028 @default.
• W4384627417 cites W3193900064 @default.
• W4384627417 cites W4224950134 @default.
• W4384627417 cites W4225405705 @default.
• W4384627417 cites W4282053982 @default.
• W4384627417 cites W4296907771 @default.
• W4384627417 cites W4308897973 @default.
• W4384627417 cites W4308944249 @default.
• W4384627417 cites W4315631504 @default.
• W4384627417 cites W4319162181 @default.
• W4384627417 doi "https://doi.org/10.1063/5.0152215" @default.
• W4384627417 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37462285" @default.
• W4384627417 hasPublicationYear "2023" @default.
• W4384627417 type Work @default.
• W4384627417 citedByCount "0" @default.
• W4384627417 crossrefType "journal-article" @default.
• W4384627417 hasAuthorship W4384627417A5024088138 @default.
• W4384627417 hasAuthorship W4384627417A5074882900 @default.
• W4384627417 hasAuthorship W4384627417A5088793872 @default.
• W4384627417 hasBestOaLocation W43846274171 @default.
• W4384627417 hasConcept C118615104 @default.
• W4384627417 hasConcept C121332964 @default.
• W4384627417 hasConcept C121864883 @default.
• W4384627417 hasConcept C139287275 @default.
• W4384627417 hasConcept C173523689 @default.
• W4384627417 hasConcept C32909587 @default.
• W4384627417 hasConcept C33923547 @default.

• next