Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
Meena has exactly the same core issue as ELIZA: it doesn't build a model of what it or the interlocutor has said, and it often contradicts what happened a few turns earlier. Topic without understanding in 1965, topic without understanding in 2020. Here's a sample:pic.twitter.com/xiCFd3Dv84
-
to defend
#deeplearning@deepmind's@felixhill84 pretends DL is only 10 years old! Perceptrons date to 1958; DL to 1967 & "logical argument” below grossly misrepresents my position, which says we need *much more* than just hybrid architecture. from http://rebooting.ai : 1/2 https://twitter.com/FelixHill84/status/1221360053971771393 …pic.twitter.com/8LpDJzweQb
Prikaži ovu nit -
Coming Soon-ish: The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence First draft almost done!pic.twitter.com/Bg3tQ1trzH
-
i think people can actually represent fragments of FOL (or something close to it) just fine, up to limits on memory. look at my
@jeffclune slide in debate for example; given a moments’ background, the universally quantified sentence in top right can be easily represented:pic.twitter.com/ijv6GIyrAO
-
Warning: slightly out of control narrative about GPT-2 & chess spreading rapidly! - system has not properly induced rules; serious problems sticking to legal moves - relies heavily on large opening library - failures in keeping track of state akin to my NeurIPS talk (ex. below) https://twitter.com/TomChivers/status/1214488063310741504 …pic.twitter.com/OD7g3DN7ho
-
Hinton has not really articulated his arguments, so much as ridiculed his opposition, not really allowing any quarter for prior value, eg::pic.twitter.com/W9GZc6J0uE
-
didn’t say it was surprising; said it was huge: direct confirmation of something Christof Koch among others had speculated for a long time. the world now is full of stuff like the below (emphasize on “sums”) assuming this paper is replicated & extended, thinking will change.pic.twitter.com/wnVbAujp0v
-
Perceptive comments on yesterday's Bengio-Marcus dialog, from the computer vision research Yiannis Aloimonos, judging the outcome a tie and suggesting value in meeting in the middle.pic.twitter.com/5NmeWgrbeu
-
i was specifically responding to this ref of yours to mouse:pic.twitter.com/GWZHK0fDp9
-
this is my world: a reporter asks Hinton about symbolic hybrids, Hinton likens them to a dying relic I then strenuously defend position that such hybrids are still worth considering and then? people attack me for suggesting that anyone might have a bias against symbols.
https://twitter.com/jasonj955/status/1211846159024762881 …pic.twitter.com/UPyYOB9nan
-
As this decade comes to a close, and apropos the
#AIDebate, I want to repeat one of the first things that I wrote in the last decade, because looking more broadly than we have looked, still strikes me as the best way forward:pic.twitter.com/bBoq3xUZwA
-
see other reply; you are misinterpreting me. if you want to attack fine, but don’t attack me where i am asking people to nominate their favorite alternatives:pic.twitter.com/EIc6mUGxQb
-
sorry but no; you are distorting things. i said shame on you for trying to stifle a conversation about alternatives by attacking me & trying to divert conversation from a productive discussion of alternatives that many contributed to. compare your tweet to the query i posed below https://twitter.com/tobias_rees/status/1211826605997211648 …pic.twitter.com/pClhVGrZyy
-
what do you think of yoshua’s definition here? doesn’t it subsume your approach into deep learning, if you accept the definition?pic.twitter.com/e8gcboJXAo
-
yep people differ in what world models they build. but they don't differ in *whether* they build world models. we all do it every time we read a book or an article or watch a story. GPT-2 never does, not in the sense my kids do. which is why it struggles with stuff like this:pic.twitter.com/YdbdKKN1zO
-
Lost in the debate: it may have sounded like I think hybrid models are sufficient for general AI. I don't. Hybrids are necessary; not sufficient. Rx given in http://rebooting.ai is also about eg building knowledge & frameworks for things like space, time & causality:pic.twitter.com/05XgOF1M1F
-
"Deep learning est mort": Jan 2018 blog quoting
@ylecun that partly resembles Bengio's recent definition of deep learning but instead dubs it "differentiable programming" I prefer@ylecun's framing We still need a separate way of talking about current models & their limitspic.twitter.com/4MOKJzP5ao
Prikaži ovu nit -
Just wanted to say how much I appreciate all the private notes of support that many people have been sending me.
These notes give me strength.
pic.twitter.com/VEpid6RS93
-
hybrid AI was an important strand of the book but we argue that it is necessary but not sufficient. our overall recipe:pic.twitter.com/NKa18GYlpv
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.