期刊
MATHEMATICS
卷 11, 期 6, 页码 -出版社
MDPI
DOI: 10.3390/math11061417
关键词
neural network; variational Monte Carlo; quantum chemistry
类别
In this paper, a single-layer fully connected neural network called tanh-FCN is proposed as a tool to solve ab initio quantum chemistry problems, adapted from the restricted Boltzmann machine (RBM). The network represents real electronic wave functions using real numbers, achieving comparable precision to RBM for various molecules. Additionally, the authors show that knowledge of the Hartree-Fock reference state can be utilized to accelerate the convergence of the variational Monte Carlo algorithm and improve the energy precision.
The restricted Boltzmann machine (RBM) has recently been demonstrated as a useful tool to solve the quantum many-body problems. In this work we propose tanh-FCN, which is a single-layer fully connected neural network adapted from RBM, 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据