Solving two and three-body systems with deep neural networks

TL;DR

This paper introduces an unsupervised deep neural network approach to solve two- and three-body bound state problems, accurately computing properties of nuclear systems without prior wave function assumptions.

Contribution

It presents a novel neural network method capable of handling both two- and three-body problems in nuclear physics, extending previous techniques and providing accurate results.

Findings

Accurately computes deuteron and triton bound states

No prior assumptions needed about wave function behavior

Potentially applicable to complex nuclear many-body problems

Abstract

We develop a new method for solving two- and three-body bound state problems using unsupervised machine learning techniques. We use a deep neural network to calculate both simple and realistic potentials, obtaining the properties of the deuteron and triton bound states for the chiral effective field theory NN potential. Our results provide significant accuracy with no prior assumptions about the behaviour of the wave function. This neural network technique, which extends from two-body to three-body, may provide insight into potential solutions to the nuclear and hadronic many-body problems.