Modeling (nuclear) quantum many-body systems with neural network quantum states

I will discuss the application of artificial neural networks as a flexible tool for compactly representing quantum many-body states of systems characterized by non-perturbative interactions, such as atomic nuclei and neutron-star matter. This approach offers a systematically improvable solution with a polynomial cost in the number of nucleons, allowing us to study emergent properties of nuclear systems, including superfluidity, clustering, and shell structures. I will also discuss the potential implications of this method for neutrino physics and gravitational-wave astronomy. In addition to the nuclear many-body problem, we will showcase applications of neural network quantum states in condensed-matter systems, such as the homogeneous electron gas and strongly interacting cold Fermi gases.