News for hackers. Stuff that matters.
Re:Why does deep and cheap learning work so well? by petters on Saturday May 12, 2018 @03:58AM (#17052984)
> we show that n variables cannot be multiplied using fewer than 2^n neurons in a single hidden layer.

I don't know, but it just feels like this should have been known in CS earlier than 2016. Circuit complexity has been studied for a long time.

Re:Why does deep and cheap learning work so well? by raverbashing on Saturday May 12, 2018 @05:28AM (#17053212)
Depends if you want an exact multiplication or not

Especially if you have neurons with non-linear response

remember ln(a*b) = ln(a)+ln(b)