Timeline for How to interpret smooth l1 loss?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 1, 2018 at 13:08 | history | edited | kjetil b halvorsen♦ | CC BY-SA 4.0 |
deleted 8 characters in body; edited tags
|
| Sep 29, 2018 at 20:52 | answer | added | Gautam Sreekumar | timeline score: 31 | |
| Jun 18, 2018 at 6:28 | history | migrated | from stackoverflow.com (revisions) | ||
| Jun 17, 2018 at 12:07 | comment | added | sascha | It tries to mimic the l1-loss (look at the graph), while being smooth. The smoothness property allows for treatment as smooth continuous optimization, which is in general easier than non-smooth opt. | |
| Jun 17, 2018 at 9:08 | history | asked | Ryan | CC BY-SA 4.0 |