I added two tags.

Link

edit approved Aug 12 at 20:40

Super Kai - Kazuya Ito

145
8

Question Protected by kjetil b halvorsen♦

occurred Jun 12, 2022 at 1:24

edited tags

Link

edited Oct 24, 2019 at 11:52

Ferdi

5.3k
10
47
64

machine-learning neural-networks deep-learning sigmoid-curve

Tweeted twitter.com/StackStats/status/1170985315978399744

occurred Sep 9, 2019 at 9:00

added 14 characters in body; edited title

Source Link

edited Apr 19, 2017 at 14:41

amoeba

107.3k
36
321
347

What are the advantages of ReLU over sigmoid function in deep neural networknetworks?

The state of the art of non-linearity is to use ReLUrectified linear units (ReLU) instead of sigmoid function in deep neural network, what. What are the advantages?

I know that training a network when ReLU is used would be faster, and it is more biological inspired, what are the other advantages? (That is, any disadvantages of using sigmoid)?

Thanks!

Source Link

asked Dec 2, 2014 at 2:13

RockTheStar

13.1k
34
73
96

Loading

Stack Exchange Network

Return to Question

What are the advantages of ReLU over sigmoid function in deep neural networknetworks?

What are the advantages of ReLU over sigmoid function in deep neural network?

What are the advantages of ReLU over sigmoid function in deep neural networks?