Vapnik–Chervonenkis dimension: Difference between revisions
(Created page with " just storing tabs here for now: * https://en.wikipedia.org/wiki/VC_dimension * https://www.quora.com/Explain-VC-dimension-and-shattering-in-lucid-Way * https://www.google.co...") |
No edit summary |
||
| Line 17: | Line 17: | ||
* does this work with more than two labels? | * does this work with more than two labels? | ||
* in the adversarial perspective, why do you get to pick the points? (this is a question about which definition is most useful.) is there a name for the thing where you can separate ''all'' points and all labels? | |||
* where does the hypothesis class come from? it seems like "lines", "circles", "convex sets" are some examples used. | |||
Revision as of 05:20, 8 July 2018
just storing tabs here for now:
- https://en.wikipedia.org/wiki/VC_dimension
- https://www.quora.com/Explain-VC-dimension-and-shattering-in-lucid-Way
- https://www.google.com/search?q=VC%20dimension
- https://en.wikipedia.org/wiki/Shattered_set
- https://math.stackexchange.com/questions/96655/how-to-calculate-vapnik-chervonenkis-dimension
I think there's three different "views" of the VC dimension:
- in terms of sets/powersets and shattering
- in terms of fitting parameters for a function
- adversarial/game: to show the VC dimension is at least n: you choose n points, the adversary chooses the labels, you must find a hypothesis from the hypothesis class that separates the labels cleanly
questions:
- does this work with more than two labels?
- in the adversarial perspective, why do you get to pick the points? (this is a question about which definition is most useful.) is there a name for the thing where you can separate all points and all labels?
- where does the hypothesis class come from? it seems like "lines", "circles", "convex sets" are some examples used.