Re:Why does deep and cheap learning work so well?
by crb002 on Friday May 11, 2018 @07:11PM
(#17051373)
Learning a transformation from the full transformation semigroup is the most general case. Consider a mystery unary CPU operation M on a 64 bit register. How deep of a circuit do you need to calculate any such transformation M? According to Kolmogorov just writing out a random transformation function takes (2^64)*(64) bits to make the lookup table. log of that to get a result out efficiently. Results here were already proved in information theory. If you use a depth less than log of the lookup table you are screwed unless your function is extremely non-random.
[ Parent
| on HN ]
Re:Why does deep and cheap learning work so well?
by zerostar07 on Sunday May 13, 2018 @03:47AM
(#17057794)
it's not the same results, their point was to justify it on physical grounds