I don't think that this is true. You need an infinite number of dimensions for t... | Hacker News

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

Mithriil 62 days ago | parent | context | favorite | on: There Will Be a Scientific Theory of Deep Learning

I don't think that this is true. You need an infinite number of dimensions for this (think Taylor's expansion, Fourier expansion, infinitely wide or deep NNs..)

jmalicki 62 days ago [–]

Yes, you do linear interpolation between an infinite number of data points.

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