We study the problem of computing the preimage of a set under a neural network with piecewise-affine activation functions. We recall an old result that the preimage of a polyhedral set is again a union of polyhedral sets and can be effectively computed. We show several applications of computing the preimage for analysis and interpretability of neural networks.
@article{arxiv.2308.14093,
title = {The inverse problem for neural networks},
author = {Marcelo Forets and Christian Schilling},
journal= {arXiv preprint arXiv:2308.14093},
year = {2023}
}