Programs in Physics & Physical Chemistry
|[Licence| Download | New Version Template] afak_v1_0.tar.gz(1379 Kbytes)|
|Manuscript Title: Amp: A modular approach to machine learning in atomistic simulations|
|Authors: Alireza Khorshidi, Andrew Peterson|
|Program title: Amp|
|Catalogue identifier: AFAK_v1_0|
Distribution format: tar.gz
|Journal reference: Comput. Phys. Commun. 207(2016)310|
|Programming language: Python, Fortran.|
|Computer: PC, Mac.|
|Operating system: Linux, Mac, Windows.|
|Has the code been vectorised or parallelized?: Yes|
|RAM: Variable, depending on the number and size of atomic systems.|
|Keywords: Potential energy surface, Neural networks, Atomic Simulation Environment (ASE), Density functional theory, Zernike polynominals.|
|Classification: 16.1, 2.1.|
External routines: ASE, NumPy, SciPy, f2py, matplotlib
Nature of problem:
Atomic interactions within many-body systems typically have complicated functional forms, difficult to represent in simple pre-decided closed-forms.
Machine learning provides flexible functional forms that can be improved as new situations are encountered. Typically, interatomic potentials yield from machine learning simultaneously apply to different system sizes.
Amp is as modular as possible, providing a framework for the user to create atomic environment descriptor and regression model at will. Moreover, it has Atomic Simulation Environment (ASE) interface, facilitating interactive collaboration with other electronic structure calculators within ASE.
Variable, depending on the number and size of atomic systems.
|Disclaimer | ScienceDirect | CPC Journal | CPC | QUB|