Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099005864> ?p ?o ?g. }
- W3099005864 endingPage "014106" @default.
- W3099005864 startingPage "014106" @default.
- W3099005864 abstract "Fragmentation methods such as the many-body expansion (MBE) are a common strategy to model large systems by partitioning energies into a hierarchy of decreasingly significant contributions. The number of fragments required for chemical accuracy is still prohibitively expensive for ab-initio MBE to compete with force field approximations for applications beyond single-point energies. Alongside the MBE, empirical models of ab-initio potential energy surfaces have improved, especially non-linear models based on neural networks (NN) which can reproduce ab-initio potential energy surfaces rapidly and accurately. Although they are fast, NNs suffer from their own curse of dimensionality; they must be trained on a representative sample of chemical space. In this paper we examine the synergy of the MBE and NN's, and explore their complementarity. The MBE offers a systematic way to treat systems of arbitrary size and intelligently sample chemical space. NN's reduce, by a factor in excess of $10^6$ the computational overhead of the MBE and reproduce the accuracy of ab-initio calculations without specialized force fields. We show they are remarkably general, providing comparable accuracy with drastically different chemical embeddings. To assess this we test a new chemical embedding which can be inverted to predict molecules with desired properties." @default.
- W3099005864 created "2020-11-23" @default.
- W3099005864 creator A5008391873 @default.
- W3099005864 creator A5026991176 @default.
- W3099005864 creator A5032970928 @default.
- W3099005864 date "2017-01-07" @default.
- W3099005864 modified "2023-09-25" @default.
- W3099005864 title "The many-body expansion combined with neural networks" @default.
- W3099005864 cites W116751493 @default.
- W3099005864 cites W1498436455 @default.
- W3099005864 cites W1531674615 @default.
- W3099005864 cites W1536778493 @default.
- W3099005864 cites W1584846110 @default.
- W3099005864 cites W1596185547 @default.
- W3099005864 cites W1911433256 @default.
- W3099005864 cites W1966939946 @default.
- W3099005864 cites W1974672343 @default.
- W3099005864 cites W1975997599 @default.
- W3099005864 cites W1976011815 @default.
- W3099005864 cites W1976147568 @default.
- W3099005864 cites W1977668506 @default.
- W3099005864 cites W1982598895 @default.
- W3099005864 cites W1984600589 @default.
- W3099005864 cites W1992531741 @default.
- W3099005864 cites W1995901124 @default.
- W3099005864 cites W1996014895 @default.
- W3099005864 cites W1996649201 @default.
- W3099005864 cites W1998260904 @default.
- W3099005864 cites W2004829031 @default.
- W3099005864 cites W2005205193 @default.
- W3099005864 cites W2008000132 @default.
- W3099005864 cites W2015541791 @default.
- W3099005864 cites W2015960758 @default.
- W3099005864 cites W2017147092 @default.
- W3099005864 cites W2020786104 @default.
- W3099005864 cites W2025444507 @default.
- W3099005864 cites W2026172453 @default.
- W3099005864 cites W2029347372 @default.
- W3099005864 cites W2029413789 @default.
- W3099005864 cites W2030582758 @default.
- W3099005864 cites W2031694014 @default.
- W3099005864 cites W2033777798 @default.
- W3099005864 cites W2034097448 @default.
- W3099005864 cites W2037566781 @default.
- W3099005864 cites W2044990793 @default.
- W3099005864 cites W2051376093 @default.
- W3099005864 cites W2051995056 @default.
- W3099005864 cites W2052512084 @default.
- W3099005864 cites W2055357173 @default.
- W3099005864 cites W2056286580 @default.
- W3099005864 cites W2058370262 @default.
- W3099005864 cites W2061721205 @default.
- W3099005864 cites W2062227835 @default.
- W3099005864 cites W2063007245 @default.
- W3099005864 cites W2064033756 @default.
- W3099005864 cites W2067050455 @default.
- W3099005864 cites W2068304618 @default.
- W3099005864 cites W2068473123 @default.
- W3099005864 cites W2068644111 @default.
- W3099005864 cites W2071267590 @default.
- W3099005864 cites W2073612718 @default.
- W3099005864 cites W2074616700 @default.
- W3099005864 cites W2075093176 @default.
- W3099005864 cites W2075274454 @default.
- W3099005864 cites W2079171230 @default.
- W3099005864 cites W2081459370 @default.
- W3099005864 cites W2083415705 @default.
- W3099005864 cites W2090204641 @default.
- W3099005864 cites W2094560786 @default.
- W3099005864 cites W2104489082 @default.
- W3099005864 cites W2105616783 @default.
- W3099005864 cites W2108968495 @default.
- W3099005864 cites W2109874343 @default.
- W3099005864 cites W2111182549 @default.
- W3099005864 cites W2114416296 @default.
- W3099005864 cites W2121076213 @default.
- W3099005864 cites W2123952737 @default.
- W3099005864 cites W2134164499 @default.
- W3099005864 cites W2148941593 @default.
- W3099005864 cites W2159357141 @default.
- W3099005864 cites W2171047927 @default.
- W3099005864 cites W2185811075 @default.
- W3099005864 cites W2226190275 @default.
- W3099005864 cites W2276944336 @default.
- W3099005864 cites W2317050189 @default.
- W3099005864 cites W2317491514 @default.
- W3099005864 cites W2323458937 @default.
- W3099005864 cites W2323493080 @default.
- W3099005864 cites W2326944644 @default.
- W3099005864 cites W2328018088 @default.
- W3099005864 cites W2341163471 @default.
- W3099005864 cites W2406709014 @default.
- W3099005864 cites W2440883851 @default.
- W3099005864 cites W2462003543 @default.
- W3099005864 cites W2465416361 @default.
- W3099005864 cites W2511310272 @default.
- W3099005864 cites W3101510464 @default.
- W3099005864 cites W3102271855 @default.