Piecewise linear activations substantially shape the loss surfaces of neural networks

Fengxiang He, Bohan Wang, Dacheng Tao. Piecewise linear activations substantially shape the loss surfaces of neural networks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. [doi]

Abstract

Abstract is missing.