The Loss Surfaces of Neural Networks with General Activation Functions

8 Apr 2020Nicholas P. BaskervilleJonathan P. KeatingFrancesco MezzadriJoseph Najnudel

We present results extending the foundational work of Choromanska et al (2015) on the complexity of the loss surfaces of multi-layer neural networks. We remove the strict reliance on specifically ReLU activation functions and obtain broadly the same results for general activation functions... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper