NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:1145
Title:Random deep neural networks are biased towards simple functions

The reviewers agreed that this was a very interesting submission, well-written and elegant, with a significant theoretical advance in our understanding of the effectiveness of neural networks. This advance nicely builds on previous empirical work by bringing theory to bear on explaining phenomena previously only demonstrated experimentally.