A visual proof that neural nets can approximate any function

Re:A visual proof that neural nets can approximate any function by braised_babbage on Saturday April 20, 2019 @06:35PM (#19709332)

One of the things about continuous functions is that they aren't necessarily differentiable, cf. https://en.wikipedia.org/wiki/Weierstrass_function

[ Parent | on HN ]

Re:A visual proof that neural nets can approximate any function by throwawaymath on Saturday April 20, 2019 @08:06PM (#19709707)

True, but that was kind of an afterthought of my point. All continuous functions still comprise a vector space.

[ Parent | on HN ]

Re:A visual proof that neural nets can approximate any function by soVeryTired on Sunday April 21, 2019 @05:44AM (#19711353)

I don't see how that helps?

> A neural network computes linear transformations

They compute a nonlinear function of an affine transform. Neural networks are nonlinear functions.

[ Parent | on HN ]