Timeline for Does it make sense to expect zero mean and standard deviation 1 for errors from a gaussian process model?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 3, 2021 at 1:05 | vote | accept | ak_nama | ||
| Feb 6, 2021 at 14:13 | answer | added | Tim | timeline score: 1 | |
| S Feb 6, 2021 at 13:51 | history | suggested | MarianD | CC BY-SA 4.0 |
Formatting
|
| Feb 6, 2021 at 13:18 | review | Suggested edits | |||
| S Feb 6, 2021 at 13:51 | |||||
| Feb 6, 2021 at 0:21 | comment | added | Henry | If what you did was standardise the training data, then you were not standardising the errors, and you would hope that the model makes the errors smaller than if you simply guessed $(0,0,0)$ for everything | |
| Feb 5, 2021 at 23:13 | history | edited | ak_nama | CC BY-SA 4.0 |
edited title
|
| Feb 5, 2021 at 23:12 | review | First posts | |||
| Feb 6, 2021 at 13:18 | |||||
| Feb 5, 2021 at 23:07 | history | asked | ak_nama | CC BY-SA 4.0 |