Timeline for What to do if CNN cannot overfit a training set on adding dropout?
Current License: CC BY-SA 3.0
24 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 22, 2021 at 2:59 | answer | added | Tom Charles Zhang | timeline score: 2 | |
| Oct 4, 2020 at 17:07 | 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. | |
| Sep 4, 2020 at 17:06 | answer | added | Gerry P | timeline score: 1 | |
| Sep 4, 2020 at 8:28 | comment | added | Karan Dhingra | What's the size of your output layer? Also, I guess with overfitting you imply zero training error?? I would suggest adding dropout before the last hidden layer. P.S. writing as an answer, because I am unable to post comments | |
| Sep 4, 2020 at 7:05 | 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. | |
| May 7, 2020 at 6:05 | 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. | |
| Dec 8, 2019 at 19:03 | 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 10, 2019 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. | |
| Apr 12, 2019 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. | |
| Dec 13, 2018 at 17:02 | 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. | |
| Nov 13, 2018 at 16:02 | 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. | |
| Oct 15, 2018 at 2:45 | comment | added | Stella Biderman | What do you think “overfit” means? I suspect that you’re using the term incorrectly. In particular, overfitting is bad. | |
| Oct 14, 2018 at 16:49 | comment | added | Martin Thoma | Can you overfit with no dropout but half the neurons? Can you overfit with double the amount of neurons and 50% dropout? | |
| Oct 14, 2018 at 16:00 | 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. | |
| Sep 14, 2018 at 16:00 | 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 15, 2018 at 15:00 | 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. | |
| Jul 16, 2018 at 14:46 | 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. | |
| Jun 16, 2018 at 14:46 | 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. | |
| May 17, 2018 at 14:39 | answer | added | Simbarashe Timothy Motsi | timeline score: 0 | |
| May 16, 2018 at 10:24 | 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. | |
| Apr 16, 2018 at 9:57 | 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. | |
| Mar 17, 2018 at 9:35 | 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. | |
| Feb 15, 2018 at 5:55 | review | First posts | |||
| Feb 15, 2018 at 11:05 | |||||
| Feb 15, 2018 at 5:55 | history | asked | user12754 | CC BY-SA 3.0 |