Local Identifiability of Deep ReLU Neural Networks: the Theory

Published in Advances in Neural Information Processing Systems 35, 2022

Recommended citation: Bona-Pellissier, Joachim, François Malgouyres, and François Bachoc. "Local Identifiability of Deep ReLU Neural Networks: the Theory." Advances in Neural Information Processing Systems 35 (2022): 27549-27562. https://proceedings.neurips.cc/paper_files/paper/2022/hash/b0ae046e198a5e43141519868a959c74-Abstract-Conference.html

This paper is about the number 2. The number 3 is left for future work.

Download paper here

Recommended citation: Bona-Pellissier, Joachim, François Malgouyres, and François Bachoc. “Local Identifiability of Deep ReLU Neural Networks: the Theory.” Advances in Neural Information Processing Systems 35 (2022): 27549-27562.