"Well, if this is what everyone is using at NIPS, it *must* be how the brain works!"
-
-
Odgovor korisnicima @pfau @AdamMarblestone
Also,
@xaqlab would be very sad to hear that you think no one is still trying to figure out how the brain does belief propagation.0 proslijeđenih tweetova 2 korisnika označavaju da im se sviđa -
That's why I had the ~ sign in front of ~everybody (and it is anyway somewhat facetious since both communities seem quite small)! And certainly a handful or two of others still working on it. But we agree there is a major shift in the overall zeitgeist...
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Odgovor korisnicima @AdamMarblestone @xaqlab
Graphical models got cool because Microsoft Research decided to specialize in them. Deep learning got a boost from Jeff Dean creating Google Brain in 2011. Lots of these shifts in zeitgeist have to do with the funding decisions of a few big tech companies.
1 reply 0 proslijeđenih tweetova 3 korisnika označavaju da im se sviđa -
You could alternatively say "when someone pushes them hard enough to show that [some of them] can scale to real problems" -- which makes it seem at least somewhat more reasonable, less contingent/sociological
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Odgovor korisnicima @AdamMarblestone @xaqlab
Why should scaling to optimizing ads on large datacenters be a cue for neuroscientists?
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Better something than nothing
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Odgovor korisnicima @AdamMarblestone @xaqlab
Probably better to be driven by actual experimental observations from neuroscience
1 reply 0 proslijeđenih tweetova 2 korisnika označavaju da im se sviđa -
Adam Marblestone je proslijedio/a tweet korisnika/ceRodney Brooks
Adam Marblestone je dodan/na,
0 proslijeđenih tweetova 2 korisnika označavaju da im se sviđa -
Seriously though, approximate backprop seems simpler than approximate PGM inference... and many probabilistic inference problems can be re-framed as neural nets as the field is doing now
1 reply 0 proslijeđenih tweetova 0 korisnika označava da im se sviđa
And there are things like:https://www.nature.com/articles/s41467-017-00181-8 …
-
-
And PGMs have been heavily explored, while backprop was ignored for a long time... so I think things are OK
0 proslijeđenih tweetova 0 korisnika označava da im se sviđa -
But yes... basing as directly as possible in ground truth neuro observations would be very nice...
0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa - Još 2 druga odgovora
Novi razgovor -
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.