Timeline for Why are neural networks preferred to other classification functions optimized by gradient decent
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 30, 2020 at 18:08 | vote | accept | Physical Mathematics | ||
| Aug 30, 2020 at 17:02 | answer | added | nbro | timeline score: 3 | |
| Aug 30, 2020 at 2:34 | comment | added | nbro | Here is a related question What are the differences between artificial neural networks and other function approximators?. | |
| Aug 30, 2020 at 2:34 | history | edited | nbro |
edited tags
|
|
| Aug 29, 2020 at 21:38 | comment | added | user9947 | Because polynomials are limited by their degree. The approximation ability of functions are generally given by a measure called VC dimension, and 2 degree polynomials have VC dimension 2/3 (I forget the exact number). So you basically have to take infinite degree polynomial combinations. NNs can be somewhat flexible in this regard that you don't have to manually choose functions, you can pretty much approximate a polynomial within an interval given sufficient nodes. This is the general theory, there are much more detailed nuances which goes against this aforementioned theory. | |
| Aug 29, 2020 at 16:25 | review | First posts | |||
| Aug 30, 2020 at 1:40 | |||||
| Aug 29, 2020 at 16:21 | history | asked | Physical Mathematics | CC BY-SA 4.0 |