Timeline for Negative samples on multiclass neural network training
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 27, 2018 at 19:18 | history | edited | Firebug |
edited tags
|
|
| Sep 27, 2018 at 19:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 23, 2018 at 1:09 | answer | added | Sycorax♦ | timeline score: 1 | |
| Feb 17, 2015 at 15:28 | comment | added | Artem Sobolev |
Well, if your negative example belongs to some class X, then softmax (usual multiclass loss) automatically understands that it's a negative examples for every other class.
|
|
| Feb 17, 2015 at 14:52 | comment | added | npit | Appended question with the response. | |
| Feb 17, 2015 at 14:51 | history | edited | npit | CC BY-SA 3.0 |
added 282 characters in body
|
| Feb 17, 2015 at 14:14 | history | edited | Andy | CC BY-SA 3.0 |
deleted 14 characters in body
|
| Feb 17, 2015 at 14:01 | review | First posts | |||
| Feb 17, 2015 at 14:14 | |||||
| Feb 17, 2015 at 13:33 | comment | added | itdxer | What did you mean when say "Negative samples"? Can you give some example? | |
| Feb 17, 2015 at 13:12 | history | asked | npit | CC BY-SA 3.0 |