Why, in Deep Learning, Non-smooth Activation Function Works Better Than Smooth Ones - researchr publication

researchr

You are not signed in
Sign in
Sign up

Daniel Cruz, Ricardo V. Godoy, Vladik Kreinovich. Why, in Deep Learning, Non-smooth Activation Function Works Better Than Smooth Ones. In Martine Ceberio, Vladik Kreinovich, editors, Decision Making Under Uncertainty and Constraints - A Why-Book. Volume 217 of pages 111-115, Springer, 2023. [doi]

Abstract is missing.

runs on WebDSL