# Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo

## TL;DR

This paper introduces the use of feed-forward neural networks as flexible trial wave functions in quantum Monte Carlo simulations, effectively modeling both simple and fermionic many-body systems.

## Contribution

It presents a novel approach of employing neural networks for trial wave functions, incorporating antisymmetry via Slater determinants, and demonstrates its effectiveness on model systems.

## Key findings

- Neural network wave functions accurately model simple systems.
- Incorporation of antisymmetry via Slater determinants is effective.
- Method shows promise for complex many-body quantum simulations.

## Abstract

Inspired by the universal approximation theorem and widespread adoption of artificial neural network techniques in a diversity of fields, we propose feed-forward neural networks as a general purpose trial wave function for quantum Monte Carlo simulations of continous many-body systems. Whereas for simple model systems the whole many-body wave function can be represented by a neural network, the antisymmetry condition of non-trivial fermionic systems is incorporated by means of a Slater determinant. To demonstrate the accuracy of our trial wave functions, we have studied an exactly solvable model system of two trapped interacting particles, as well as the hydrogen dimer.