Timeline for What is the advantage of using cross entropy loss & softmax?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 14, 2021 at 19:26 | comment | added | S2673 | @datdinhqouc When the last layer is the sigmoid function then cross entropy should make loss convergence faster and prevent vanishing gradients. | |
| Mar 11, 2021 at 2:36 | comment | added | Dan D. | so cross entropy makes loss convergence faster, compared to mse? | |
| Oct 11, 2020 at 22:57 | history | edited | S2673 | CC BY-SA 4.0 |
added 4 characters in body
|
| Oct 11, 2020 at 22:51 | history | edited | S2673 | CC BY-SA 4.0 |
added 10 characters in body
|
| Oct 11, 2020 at 22:44 | history | answered | S2673 | CC BY-SA 4.0 |