English

A real neural network state for quantum chemistry

Quantum Physics 2023-01-11 v1

Abstract

The restricted Boltzmann machine (RBM) has been successfully applied to solve the many-electron Schro¨\ddot{\text{o}}dinger equation. In this work we propose a single-layer fully connected neural network adapted from RBM and apply it to study ab initio quantum chemistry problems. Our contribution is two-fold: 1) our neural network only uses real numbers to represent the real electronic wave function, while we obtain comparable precision to RBM for various prototypical molecules; 2) we show that the knowledge of the Hartree-Fock reference state can be used to systematically accelerate the convergence of the variational Monte Carlo algorithm as well as to increase the precision of the final energy.

Keywords

Cite

@article{arxiv.2301.03755,
  title  = {A real neural network state for quantum chemistry},
  author = {Yangjun Wu and Xiansong Xu and Dario Poletti and Yi Fan and Chu Guo and Honghui Shang},
  journal= {arXiv preprint arXiv:2301.03755},
  year   = {2023}
}
R2 v1 2026-06-28T08:08:11.778Z