Timeline for Calibrating a multi-class boosted classifier
Current License: CC BY-SA 2.5
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 17, 2021 at 14:48 | comment | added | Ben Reiniger | The paper is indeed very useful, but I think this answer doesn't accurately summarize it: in one dataset simple normalization wins, but it depends on which calibration method was used, and for another dataset normalization does not win. The conclusion is still to use simple normalization, because the others don't perform significantly better and it's simple. | |
| Jun 27, 2019 at 9:40 | comment | added | songololo | Echoing this answer. This stumped me for some time but the paper by Zadrozny and Elkan proved useful. | |
| Aug 16, 2018 at 15:14 | comment | added | TMrtSmith | Cross reference to here stats.stackexchange.com/questions/362460/… | |
| Jul 6, 2018 at 15:42 | comment | added | Chandra | Links mentioned in answer are outdated. Latest links are: citeseerx.ist.psu.edu/viewdoc/… citeseerx.ist.psu.edu/viewdoc/… | |
| Feb 2, 2011 at 14:49 | vote | accept | Amelio Vazquez-Reina | ||
| Feb 2, 2011 at 14:49 | vote | accept | Amelio Vazquez-Reina | ||
| Feb 2, 2011 at 14:49 | |||||
| Jan 28, 2011 at 13:21 | history | answered | B_Miner | CC BY-SA 2.5 |