|
ABACUS develop
Atomic-orbital Based Ab-initio Computation at UStc
|
Implementation of ESolver_NEP class for neuroevolution potential (NEP). More...
#include "esolver_nep.h"#include "source_base/parallel_common.h"#include "source_base/timer.h"#include "source_io/output_log.h"#include "source_io/cif_io.h"#include <numeric>#include <unordered_map>Implementation of ESolver_NEP class for neuroevolution potential (NEP).
#include "source_io/module_parameter/parameter.h"
This file contains the implementation of the ESolver_NEP class, which is used for solving the energy and forces in a NEP simulation. NEP is a method for training deep neural networks to accurately predict the potential energy surface of a molecular system.
For more information about NEP, see the following reference: