NN are _just_ transfer functions. Look up tables. Or really dense maps. So f(g(x... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		sitkack on Jan 6, 2018 \| parent \| context \| favorite \| on: “Deep Learning has outlived its usefulness as a bu... NN are _just_ transfer functions. Look up tables. Or really dense maps. So f(g(x)) make total sense. But I dont think these are the interesting combinations. I think giving one NN the training experience of another, plus the feedback on "correct inference" will be when on NN trains its replacement.

cs702 on Jan 6, 2018 [–]

Yes, of course. f(g(x)) was the simplest possible example I could come up with to illustrate the point :-)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact