Timeline for Why is the derivative of the activation functions in neural networks important?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 23, 2019 at 19:56 | answer | added | babkr | timeline score: 10 | |
| Aug 15, 2019 at 6:36 | history | became hot network question | |||
| Aug 15, 2019 at 0:43 | answer | added | nbro | timeline score: 4 | |
| Aug 15, 2019 at 0:39 | answer | added | Jens Classen | timeline score: 7 | |
| Aug 15, 2019 at 0:06 | history | edited | nbro | CC BY-SA 4.0 |
added 3 characters in body; edited tags; edited title
|
| Aug 14, 2019 at 23:42 | comment | added | user9947 | The 'constant.....' statement is not really correct in my opinion, or atleast the constant derivative means the model is not learning conclusion is incorrect. But the author really doesn't delve into details nor provide proper explanation, so the author probably might have a different way of interpreting it. Also it is kind of sketchy to talk about learning when the details of a learning objective commonly known as loss function is not provided. | |
| Aug 14, 2019 at 23:28 | history | edited | Mary | CC BY-SA 4.0 |
added 1 character in body
|
| Aug 14, 2019 at 23:27 | comment | added | Mary | towardsdatascience.com/… | |
| Aug 14, 2019 at 23:15 | comment | added | user9947 | Can you cite some sources so that we can get a much more detailed picture? | |
| Aug 14, 2019 at 22:30 | history | asked | Mary | CC BY-SA 4.0 |