Browsing Faculty of Engineering by Subject "Activation distribution"
Now showing items 1-1 of 1
-
ReLU and sigmoidal activation functions
(In Proc. South African Forum for Artificial Intelligence Research (FAIR2019), 2019-12)The generalization capabilities of deep neural networks are not well understood, and in particular, the influence of activation functions on generalization has received little theoretical attention. Phenomena such as ...