See also: A visual proof that neural networks can approximate any function https... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

segfaultbuserr on Dec 6, 2020 | parent | context | favorite | on: Every Model Learned by Gradient Descent Is Approxi...

See also:

A visual proof that neural networks can approximate any function

https://news.ycombinator.com/item?id=19708620

api on Dec 6, 2020 [–]

So a "neural network" is actually a type of parameterized mathematical function that can be fit to any curve including higher dimensional surfaces, etc.?

xksteven on Dec 6, 2020 | | [–]

That's correct. See https://en.wikipedia.org/wiki/Universal_approximation_theore... for more details

laingc on Dec 6, 2020 | | [–]

Yes.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact