Timeline for Is (manual) feature extraction outdated?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 31, 2019 at 14:22 | comment | added | KDecker | AFAIK up until recently manual feature extraction was needed to work with point cloud data in neural networks; voxelization and projection. Though new techniques, and specifically network layers (PointNet), can work with and generate the needed feature set automatically. But some of these methods still excel with manually generated features added per point. My favorite idea being the wave kernel signature borrowed from quantum mechanics. | |
| Oct 31, 2019 at 13:33 | answer | added | Peteris | timeline score: 2 | |
| Oct 31, 2019 at 9:11 | vote | accept | Hagbard | ||
| Oct 30, 2019 at 18:55 | history | became hot network question | |||
| Oct 30, 2019 at 12:09 | answer | added | Erwan | timeline score: 2 | |
| Oct 30, 2019 at 12:00 | answer | added | noe | timeline score: 14 | |
| Oct 30, 2019 at 11:31 | history | edited | Hagbard | CC BY-SA 4.0 |
added 205 characters in body
|
| Oct 30, 2019 at 11:09 | answer | added | DataFramed | timeline score: 11 | |
| Oct 30, 2019 at 10:52 | history | asked | Hagbard | CC BY-SA 4.0 |