Timeline for Why not using linear regression for finetuning the last layer of a neural network?
Current License: CC BY-SA 4.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 10 at 13:33 | comment | added | Ben Reiniger♦ | @Valentas or, if the NN is doing regression, the final activation function might be linear, so that the transfer learning step of refitting the last layer only is exactly linear regression, with a closed-form solution. | |
| Oct 10 at 11:03 | 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. | |
| Jun 10 at 23:04 | 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 10 at 8:05 | 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. | |
| Oct 10, 2023 at 22:00 | 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. | |
| Jun 11, 2023 at 11:00 | 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. | |
| Feb 11, 2023 at 3:02 | 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. | |
| Sep 29, 2022 at 0:05 | 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 30, 2022 at 11:05 | 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. | |
| Jan 30, 2022 at 9:35 | comment | added | Valentas | A neural network with all layers except the final frozen and with the sigmoid activation for the final is the same as logistic regression. Logistic regression is usually optimized by gradient descent. So you seem to juxtaposing two things that are actually the same thing (except in the case you want to later unfreeze the weights of the NN it makes it easier implementation-wise as in the answer). | |
| Jan 30, 2022 at 9:03 | 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. | |
| Sep 30, 2021 at 21:08 | 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 30, 2021 at 13:04 | 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 3, 2021 at 0:41 | answer | added | grov | timeline score: 0 | |
| Apr 2, 2021 at 8:35 | history | asked | Funkwecker | CC BY-SA 4.0 |