Phase Detection with Neural Networks: Interpreting the Black Box

9 Apr 2020  ·  Anna Dawid, Patrick Huembeli, Michał Tomza, Maciej Lewenstein, Alexandre Dauphin ·

Neural networks (NNs) normally do not allow any insight into the reasoning behind their predictions. We demonstrate how influence functions can unravel the black box of NN when trained to predict the phases of the one-dimensional extended spinless Fermi-Hubbard model at half-filling. Results are the first indication that the NN correctly learns an order parameter describing the transition. Moreover, we demonstrate that influence functions not only allow to check that the network trained to recognize known quantum phases can predict new unknown ones but even discloses information about the type of phase transition.

PDF Abstract