Re:A visual proof that neural nets can compute any function
by mturmon on Tuesday September 02, 2014 @02:30PM
(#8259278)
The same arguments as in the original Cybenko paper, or the Stone-Weierstrass theorem, lend support to the idea that SVMs are universal approximators (with most typical kernels). This has been proven by a couple of authors.
I'm not aware of universal approximation results for random forests, but since they have the same general construction, this would not be surprising.
I'm not aware of universal approximation results for random forests, but since they have the same general construction, this would not be surprising.