Timeline for Why is cross entropy not a common evaluation metric for model performance?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 25, 2020 at 11:08 | comment | added | Narfanar | How about $e^{CE}$? I think that'd be the geometric-mean of the absolute differences between $1.0$ and the predicted prob for the correct class? | |
| Oct 19, 2018 at 22:07 | vote | accept | user695652 | ||
| Oct 19, 2018 at 4:02 | history | bounty ended | CommunityBot | ||
| Oct 11, 2018 at 13:17 | history | answered | gazza89 | CC BY-SA 4.0 |