10-15 yrs ago, appears ~everybody talking cortical implementation of belief prop, ~nobody talking cortical implementation of back prop: https://scholar.google.com/scholar?q=related:CP4ffwsbGlcJ:scholar.google.com/&scioq=Cortical+circuitry+implementing+graphical+models&hl=en&as_sdt=0,5 … (not saying this is bad -- both very inspirational algorithms -- just interesting)
-
-
Odgovor korisniku/ci @AdamMarblestone
I literally spent a whole day arguing with Blake Richards about this on Twitter a few months ago.
1 reply 0 proslijeđenih tweetova 2 korisnika označavaju da im se sviđa -
Odgovor korisnicima @pfau @AdamMarblestone
"Well, if this is what everyone is using at NIPS, it *must* be how the brain works!"
1 reply 1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa -
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
Probably better to be driven by actual experimental observations from neuroscience
-
-
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 - Još 5 drugih 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.