News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by seiji on Thursday May 21, 2015 @09:01PM (#9586174)
> Storing zeroes and ones deterministically

Turing-complete platforms are universal simulators. There's nothing they can't represent.

> like how information is flowing from short-term memory to long-term

Sure, we know that. The little seahorse helps out.

> re-purposing brain structures

rudimentary artificial neural nets do the same thing. they also self-specialize automatically with no innate programming (line detectors, edge detectors, eye detectors, cat detectors, all the way up—automatically).

> we may still be hundreds of years away

lol. nope. gotta think exponentially.

> lesser solutions if we stop seeing financial benefits, like with space exploration

can't do space exploration without the approval of a nation-state. can do AI tomfoolery in your own basement with nobody else finding out until it's too late.

Re:The Unreasonable Effectiveness of Recurrent Neural Networks by alexlarsson on Friday May 22, 2015 @10:46AM (#9588595)
> Turing-complete platforms are universal simulators. There's nothing they can't represent.

No existing computer is a universal turing machine. The infinite ram requirement is pretty hard to implement in practice.