Timeline for Why cannot linear activation functions be used to approximate any function?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 9, 2022 at 13:58 | comment | added | Chillston | Right! To achieve that, we would have to partition the function which itself is a non-linearity :) | |
| Jul 9, 2022 at 13:52 | vote | accept | levitatmas | ||
| Jul 9, 2022 at 13:52 | comment | added | levitatmas | Thank you very much, great explanation and demonstration. The point is that using linear functions ( exactly, not piece-wise) and combining them in some way, we can never obtain the example function you gave right ? | |
| Jul 9, 2022 at 13:31 | history | edited | Chillston | CC BY-SA 4.0 |
deleted 1 character in body
|
| Jul 9, 2022 at 13:23 | history | answered | Chillston | CC BY-SA 4.0 |