Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
-
Really nice! For your module on generative models, I would like to suggest our RCN paper, which has exactly this kind of shape-object factorization and is an example of a neuroscience inspired predictive-coding model that works in practice. https://science.sciencemag.org/content/358/6368/eaag2612 …pic.twitter.com/CViGu8Tuzv
-
Why do you consider that image interpretation be non-compositional? It is context-sensitive and compositional , and we did tackle that problem in our RCN paper. See Fig 1C(i) where interpretation switches between 'm' and 'un', and (iii) 'bison' and 'bike' https://science.sciencemag.org/content/358/6368/eaag2612.full?ijkey=DmvGldXIEXVoQ&keytype=ref&siteid=sci …pic.twitter.com/06nWFnNoZg
-
Yes, that you don't know until you do, and you won't know unless you try. Btw, this was an article in NYT in 1903 about how far away flight is....'Flying machines that do not fly', and it is true that at that point we didn't know and it looked very far, but was just weeks away!pic.twitter.com/Uo43biWnAg
-
It is right on top as the premise of the article. :). Makes me not want to read it because it is obviously incorrect.pic.twitter.com/HDGr6yRWLb
-
The irony is that "flapping is not required to fly" was something Wright brothers learned from observing birds! They kept detailed notes about birds soaring for long distance with no movement of their wings, except for the slight twist of ends for control. https://arxiv.org/abs/1909.01561 pic.twitter.com/frbI9PYwXI
-
Very nice blog. I think neocortex uses a dozen or so general-purpose priors that help with learning and inference, and understanding how to encode those priors is an important challenge for AI...as I put it here: https://arxiv.org/abs/1909.01561 https://twitter.com/WiringTheBrain/status/1213473329769861120 …pic.twitter.com/t7vx3vFy1K
-
This snippet from your paper is interesting... see our recent work on cognitive maps where spatial representations are formed from pure sequence learning...https://www.biorxiv.org/content/10.1101/864421v2 …pic.twitter.com/UX1q90O9Co
-
Yoshua wants a new term for 'specific forms of deep learning', (which includes causality, reasoning etc?) Looks like he has almost spelled it out: Deep Learning 2.0 https://medium.com/@GaryMarcus/deep-learning-science-engineering-research-and-terminology-292a747a94d3 …pic.twitter.com/WXwSyTE1Bv
-
#AGIcomics again hit the nail on its head!! From the recent Bengio-Marcus discussion.. (https://medium.com/@GaryMarcus/deep-learning-science-engineering-research-and-terminology-292a747a94d3 …) https://twitter.com/dileeplearning/status/1199782049810243584?s=20 …pic.twitter.com/w6WAdAqhxT
-
#AGIcomics wishes you a Happy New Year, really!pic.twitter.com/9KNbAoufQT
-
Lee & Mumford paper is a good start. http://www.cnbc.cmu.edu/~tai/papers/lee_mumford_josa.pdf …. Our RCN paper is an example of instantiating those ideas in a model. Also, see cognitive programs where visual cortex is not a passive module, but part of interactive querying of the world. https://www.vicarious.com/2019/01/18/a-thought-is-a-program/ …pic.twitter.com/EH9fy5pBRS
-
hey, but it is "evolving", are you sure PGMs won't be included in the future? Also, if PGMs weren't included Geoff could have titled this differently no?pic.twitter.com/f42M6WPuMk
-
#AGIcomics is proud to have predicted this slide from Yoshua. Just user our flow chart instead of a wall of text.... https://twitter.com/raamana_/status/1209266195678973952 …pic.twitter.com/zDgqtKGUwv
-
Of course not, because it is predicted here :)
#AGIcomicspic.twitter.com/1HNhw4u0uY
-
Artificial General Dilemma afflicts MIT Tech Review...again!
#AGIComics https://twitter.com/techreview/status/1206610721083133953 …pic.twitter.com/EZqpPphxUW
-
@GaryMarcus I liked the content except for the fact that@fchollet *systematically* avoids citing relevant work. Multiple researchers have worked on concepts as program learning. Read our blog and paper to see the similarities to our recent work: https://www.vicarious.com/2019/01/18/a-thought-is-a-program/ …pic.twitter.com/6kxfRZRO1Q
-
Have you seen this paper? I can confirm that it is hard to stay out of the extremes in this :) https://link.springer.com/article/10.3758/s13423-016-1028-3 …pic.twitter.com/RCdom0on5I
-
Actually I take that comment back because look how cute those agents are....awwwpic.twitter.com/X2TvgVyavJ
-
When I am as successful as Yoshua Bengio, I will write a paper with the title 'The Pretentious Prior' ...and kinda get away with it :) https://arxiv.org/abs/1709.08568 pic.twitter.com/liM3rCdZQE
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.