Artificial neural network quantum states for atomic nuclei

Due to the exponential complexity of the many-body problem, solving the nuclear Schrödinger equation beyond light nuclei necessarily involves approximations. In this talk, we present a novel variational Monte Carlo method based on Artificial Neural Network representations of the ground-state wave functions that reach state-of-the-art precisions on light systems and favorably scale with the number of nucleons. We successfully benchmark nuclear binding energies, point-nucleon densities, and radii with the highly-accurate Green's function Monte Carlo and hyperspherical harmonics methods. The extensions of our approach to larger nuclei, including ¹⁶O, and periodic systems, will also be discussed.