News for hackers. Stuff that matters.
Re:Alibaba neural network defeats human in global reading test by mark_l_watson on Monday January 15, 2018 @01:38PM (#16152410)
Great result. At my job I manage a machine learning team and so I am fairly much all-in for deep learning to solve practical problems.

That said, I think the path to 'real' AGI lies in some combination of DL, probabilistic graph models, symbolic systems, and something we have not even imagined yet. BTW, a good paper just released on the limitations of DL by Judea Pearl https://arxiv.org/abs/1801.04016

Re:Alibaba neural network defeats human in global reading test by jacquesm on Monday January 15, 2018 @02:10PM (#16152627)
> That said, I think the path to 'real' AGI lies in some combination of DL, probabilistic graph models, symbolic systems, and something we have not even imagined yet.

Well, that really made it much clearer to me ;)

Re:Alibaba neural network defeats human in global reading test by ianamartin on Monday January 15, 2018 @03:39PM (#16153231)
He just means all the things that we already know don't work + something that we don't know about yet that will. (emphasis on the part we have no fucking clue about).
Re:Alibaba neural network defeats human in global reading test by bitL on Monday January 15, 2018 @08:15PM (#16155030)
I definitely hope we invent something better than vaguely defined PGMs that are a nightmare to get right and usable.
Re:Alibaba neural network defeats human in global reading test by arstin on Monday January 15, 2018 @02:11PM (#16152638)
Wow thanks for that Pearl link! I know how I'll be spending my afternoon......