Ctrl K

QMCTorch

Use and design neural network ansatz wave function for real-space quantum Monte Carlo simulations of molecular systems.

2
contributors

Cite this software

DOI:

10.5281/zenodo.3780093

Description

  • Easily use and implement new neural network ansatz
  • Use ADF or pySCF as SCF backend
  • Use Horovod to deploy on GPU clusters

In QMCTorch the trial wave function is calculated by a small, physically motivated network. Starting from the electronic positions, R, the first layer computes the values of all atomic orbitals for all electrons. From there a linear map computes the values of all relevant molecular orbitals. A Slater Pooling mask is then applied to compute all Slater determinants that are finally combined by a fully connected layer. The Jastrow factors are computed in parallel and combined with the CI expansion to obtain the value of the wave function

Logo of QMCTorch
Keywords
Computational Chemistry
GPU
High performance computing
Machine learning
quantum chemistry
Programming languages
License
</>Source code

Participating organisations

Natural Sciences & Engineering
Natural Sciences & Engineering
Netherlands eScience Center

Reference papers

Contributors

Contact person

Nicolas Renaud
Felipe Zapata
Felipe Zapata

Related projects

A light in the dark

Quantum Monte Carlo meets solar energy conversion

Updated 34 months ago
Finished