 The quantum-mini-body problem is a challenge due to its high dimensionality. However, modern machine learning models such as deep neural networks are able to represent highly correlated functions in large-dimensional spaces. By representing wave functions as a stochastically generated set of sample points, the problem of finding ground states can be reduced to a regression task. This allows for the anti-symmetry of fermions or bosons to be learned rather than enforced, making the problem more robust and computationally scalable. Additionally, the propagation of an ansatz towards the ground state can be performed in a more efficient manner than traditional variational approaches. This article was offered by Christiana Atanasova, Liam Bernheimer, and Guy Cohen.