# Reverse-Engineering Deep ReLU Networks

2 Oct 2019David RolnickKonrad P. Kording

It has been widely assumed that a neural network cannot be recovered from its outputs, as the network depends on its parameters in a highly nonlinear way. Here, we prove that in fact it is often possible to identify the architecture, weights, and biases of an unknown deep ReLU network by observing only its output... (read more)

PDF Abstract