News for hackers. Stuff that matters.
Re:A visual proof that neural nets can compute any function by Tloewald on Tuesday September 02, 2014 @06:07PM (#8260458)
Can't the same be said for Fourier series, which make no claims to be some kind of AI? And likewise humble polynomials:

http://en.wikipedia.org/wiki/Stone%E2%80%93Weierstrass_theor...

Re:A visual proof that neural nets can compute any function by mtdewcmu on Tuesday September 02, 2014 @06:50PM (#8260620)
Yes (I am not expert in neural nets, but that appears to be exactly what this is saying). If you look at what goes into a neural net and compare it to what goes into a Fourier transform, it should be obvious that neural nets have even more than they actually need to do this task.
Re:A visual proof that neural nets can compute any function by j2kun on Friday September 05, 2014 @09:30AM (#8273731)
This statement doesn't make sense to me. A neural network literally can't produce anything besides a continuous function, and the universality theorem says that there is no continuous function they can't (approximately) produce.

So what could you possibly mean when you say neural networks have "more" than they need to do something which characterizes exactly what they can and can't do?

Re:A visual proof that neural nets can compute any function by mtdewcmu on Monday September 08, 2014 @03:45AM (#8283764)
There are more coefficients than necessary. The FT has the minimum; it's bijective.