Baryons as solitons in the meson spectrum: A machine learning perspective

Abstract

Quantum chromodynamics (QCD) is the theory of the strong interaction. The fundamental particles of QCD, quarks and gluons, carry color charge and form colorless bound states at low energies. The hadronic bound states of primary interest to us are mesons and baryons. A modern approach to computing hadron masses relies on the computationally intensive framework of lattice QCD. In cases where the exact quark composition or other quantum numbers of hadronic states are not precisely known, the prediction of masses from theoretical first principles is especially challenging. We address the problem of creating accurate and interpretable models of hadronic masses without resorting to extensive numerical computations. In this study, we construct a model of hadronic masses using both Bayesian and non-Bayesian techniques in machine learning. From knowledge of the meson spectrum only, neural networks and Gaussian processes predict the masses of baryons with 90.3% and 96.6% accuracy, respectively. We also predict the masses of pentaquarks and other exotic hadrons and demonstrate that machine learning is an effective tool for testing composition hypotheses. Our results surpass the benchmark constituent quark model both in terms of accuracy of predictions and hypothesis testing across all sectors of hadrons. We anticipate that our methods could yield a mass formula for hadrons from quark composition and other quantum numbers.