Timeline for Why is the hyperbolic tangent with MSE better than the sigmoid with cross-entropy?
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 27, 2020 at 6:55 | comment | added | feature_engineer | So, he's saying the problem with MSE is that the gradients get smaller when the predictions are close to 1 and 0, and so the network might get stuck on these outputs even when they're wrong? I don't see why cross entropy is different in this regard... He said that it applies to softmax and that the math is very cool, but didn't elaborate. Can you expand on his explanation, and also apply it to tanh? | |
| Nov 16, 2019 at 19:05 | history | edited | nbro | CC BY-SA 4.0 |
added 32 characters in body
|
| Nov 16, 2019 at 18:57 | history | edited | nbro | CC BY-SA 4.0 |
added 57 characters in body
|
| Mar 2, 2018 at 17:17 | history | edited | user2674414 | CC BY-SA 3.0 |
added 3 characters in body
|
| Mar 2, 2018 at 17:05 | vote | accept | Arnaldo Gualberto | ||
| Mar 2, 2018 at 14:58 | review | First posts | |||
| Mar 2, 2018 at 17:22 | |||||
| Mar 2, 2018 at 14:53 | history | answered | user2674414 | CC BY-SA 3.0 |