Timeline for Is it better to split sequences into overlapping or non-overlapping training samples?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Oct 17, 2020 at 10:41 | history | bounty ended | Thomas Wagenaar | ||
| S Oct 17, 2020 at 10:41 | history | notice removed | Thomas Wagenaar | ||
| Oct 16, 2020 at 1:21 | answer | added | usεr11852 | timeline score: 4 | |
| Oct 15, 2020 at 20:00 | comment | added | Christian Hennig | Overlapping will increase dependence even more, but avoiding it is not enough to have independence. The idea to have longer breaks to reduce autocorrelation is not bad but your description doesn't look like you can ever be sure that no correlation or dependence is left, so ultimately you have to deal with dependence whatever you do, unless you only use one training sample per sequence (assuming that at least different sequences are independent). | |
| Oct 15, 2020 at 19:54 | comment | added | Christian Hennig | I'd suspect that there is quite some dependence within the same sequence. This means that whatever way you use subsequences from the same sequence, this will not give you independent training data, so their number will not really reflect the amount of training information you have generated, and it seems to me that this dependence somehow needs to be modelled in order to make good use of different subsamples from the same sequence. Ultimately this depends on the nature of your data. | |
| Oct 10, 2020 at 13:09 | history | edited | Thomas Wagenaar | CC BY-SA 4.0 |
deleted 9 characters in body
|
| S Oct 9, 2020 at 14:39 | history | bounty started | Thomas Wagenaar | ||
| S Oct 9, 2020 at 14:39 | history | notice added | Thomas Wagenaar | Draw attention | |
| Oct 7, 2020 at 7:53 | history | asked | Thomas Wagenaar | CC BY-SA 4.0 |