Timeline for Does the universal approximation theorem apply to ReLu?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 24, 2021 at 20:00 | history | became hot network question | |||
| May 24, 2021 at 15:04 | answer | added | Ben Reiniger | timeline score: 8 | |
| May 24, 2021 at 13:22 | comment | added | Patrick Bormann | I may be not correct but ReLu is bounded below and unbounded above. Hornik at least mentions at page 253 in the bottom, that their theorem does not account for all unbounded activation functions. The behavior of an unbounded tail function is also highlighted. So I would "guess" ReLu falls into tha category, where this theorem can not account for all unbounded activation functions | |
| May 24, 2021 at 12:20 | answer | added | Dave | timeline score: 1 | |
| May 24, 2021 at 12:06 | review | First posts | |||
| May 24, 2021 at 15:13 | |||||
| May 24, 2021 at 11:57 | history | asked | krvger | CC BY-SA 4.0 |