A Machine Learning Approach to Trapped Many-Fermion Systems

We apply a variational Ansatz based on neural networks to the problem of spin-$1\mathrm{/}2$ fermions in a harmonic trap interacting through a short distance potential. We showed that standard machine learning techniques lead to a quick convergence to the ground state, especially in weakly coupled cases. Higher couplings can be handled efficiently by increasing the strength of interactions during “training”.