Timeline for Why are mini-batches degrading my conv net MNIST classifier?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| 16 hours ago | 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 14 at 9:06 | 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 28, 2022 at 13:08 | 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. | |
| Apr 10, 2021 at 16:05 | 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. | |
| Mar 15, 2021 at 9:53 | comment | added | dontloseyourgoalie | I'm not sure what you mean by "the number of weight updates is the same", but yes, i am averaging gradients, including weight gradients during updating. But i no longer have this problem with the network since i've changed some things. I dont know what the problem was though. | |
| Mar 10, 2021 at 17:45 | comment | added | Oxbowerce | Assuming that the gradients are averaged when using mini-batches, have you made sure that the number of weight updates is the same? | |
| Mar 10, 2021 at 17:42 | history | edited | Ethan | CC BY-SA 4.0 |
added 28 characters in body
|
| Feb 12, 2021 at 20:36 | history | edited | Ethan |
edited tags
|
|
| Feb 4, 2021 at 20:16 | answer | added | Alex | timeline score: 0 | |
| Feb 4, 2021 at 19:25 | history | asked | dontloseyourgoalie | CC BY-SA 4.0 |