Skip to main content
13 events
when toggle format what by license comment
Sep 16, 2022 at 13:34 history edited user29169
edited tags
Sep 27, 2020 at 22:28 history closed Graph4Me Consultant
user29169
fuwiak
Zephyr
desertnaut
Needs details or clarity
Sep 27, 2020 at 2:10 review Close votes
Sep 27, 2020 at 22:28
Sep 25, 2020 at 13:04 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
May 26, 2020 at 20:07 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Jan 27, 2020 at 19:02 history bumped CommunityBot This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
Dec 23, 2019 at 22:27 comment added Akavall I am not an expert, but as far as I can tell, there is not enough information in the question to answer the part about activation functions. For hidden layers, ReLU seems to be default choice, but Tanh and Sigmoid could also be fine, the best way is to try and see. For output layer, you could answer it (linear for regression, sigmoid for binary classification, softmax for multi-class problem), but the question does not specify the type of output being generated.
Dec 23, 2019 at 8:07 answer added Noah Weber timeline score: 0
Dec 23, 2019 at 5:18 history edited x89 CC BY-SA 4.0
added 274 characters in body
Dec 23, 2019 at 5:15 comment added x89 @Akavall My idea was that (20*10) + (10*5) + (biases = 10+5) = 265. So 265 should be the number of parameters. For shapes/activation functions, from what I understand, it just depends on the data, no? Couldn't think of any way to directly predict it from this limited information.
Dec 23, 2019 at 0:56 comment added Akavall What do you think the answer should be?
Dec 22, 2019 at 22:40 review First posts
Dec 22, 2019 at 23:09
Dec 22, 2019 at 22:38 history asked x89 CC BY-SA 4.0