SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Frauenheim T)
 

Sökning: WFRF:(Frauenheim T) > (2020-2023) > Fortnet, a software...

Fortnet, a software package for training Behler-Parrinello neural networks

van der Heide, T. (författare)
Univ Bremen, Bremen Ctr Computat Mat Sci, Bremen, Germany.
Kullgren, Jolla, 1978- (författare)
Uppsala universitet,Strukturkemi
Broqvist, Peter (författare)
Uppsala universitet,Strukturkemi
visa fler...
Bacic, V. (författare)
Jacobs Univ Bremen, Dept Phys & Earth Sci, Campus Ring 1, D-28759 Bremen, Germany.
Frauenheim, T. (författare)
Univ Bremen, Bremen Ctr Computat Mat Sci, Bremen, Germany.;Beijing Computat Sci Res Ctr, Beijing 100193, Peoples R China.;Shenzhen JL Computat Sci & Appl Res Inst CSAR, Shenzhen 518110, Peoples R China.
Aradi, B. (författare)
Univ Bremen, Bremen Ctr Computat Mat Sci, Bremen, Germany.
visa färre...
Univ Bremen, Bremen Ctr Computat Mat Sci, Bremen, Germany Strukturkemi (creator_code:org_t)
Elsevier, 2023
2023
Engelska.
Ingår i: Computer Physics Communications. - : Elsevier. - 0010-4655 .- 1879-2944. ; 284
  • Tidskriftsartikel (refereegranskat)
Abstract Ämnesord
Stäng  
  • A new, open source, parallel, stand-alone software package (Fortnet) has been developed, which implements Behler-Parrinello neural networks. It covers the entire workflow from feature generation to the evaluation of generated potentials, coupled with higher-level analysis such as the analytic calculation of atomic forces. The functionality of the software package is demonstrated by driving the training for the fitted correction functions of the density functional tight binding (DFTB) method, which are commonly used to compensate the inaccuracies resulting from the DFTB approximations to the Kohn -Sham Hamiltonian. The usual two-body form of those correction functions limits the transferability of the parametrizations between very different structural environments. The recently introduced DFTB+ANN approach strives to lift these limitations by combining DFTB with a near-sighted artificial neural network (ANN). After investigating various approaches, we have found the combination of DFTB with an ANN acting on-top of some baseline correction functions (delta learning) the most accurate one. It allowed to introduce many-body corrections on top of two-body parametrizations, while excellent transferability to chemical environments with deviating energetics could be demonstrated.

Ämnesord

NATURVETENSKAP  -- Kemi -- Fysikalisk kemi (hsv//swe)
NATURAL SCIENCES  -- Chemical Sciences -- Physical Chemistry (hsv//eng)
NATURVETENSKAP  -- Fysik -- Den kondenserade materiens fysik (hsv//swe)
NATURAL SCIENCES  -- Physical Sciences -- Condensed Matter Physics (hsv//eng)

Nyckelord

Fortnet
Fortran
Neural networks
BPNN
DFTB
Many -body repulsive

Publikations- och innehållstyp

ref (ämneskategori)
art (ämneskategori)

Hitta via bibliotek

Till lärosätets databas

Sök utanför SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy