I think that the brain almost certainly approximates gradient descent. And here is why: Any learning episode only appears to change the brain a tiny bit. 1/5
-
Prikaži ovu nit
-
Odgovor korisniku/ci @KordingLab
I thought "Intrinsic Gradient Networks", Jason Tyler Rolfe's PhD Thesis (2012, doi:10.7907/YCB7-7X24. https://resolver.caltech.edu/CaltechTHESIS:04202012-133210844 …) was an underappreciated approach to the problem of 𝛁∈
9 proslijeđenih tweetova 32 korisnika označavaju da im se sviđa -
Odgovor korisniku/ci @BAPearlmutter
Omg. Why didn't I know of it!
0 proslijeđenih tweetova 5 korisnika označava da im se sviđa -
Odgovor korisnicima @KordingLab @BAPearlmutter
Ditto!
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Fascinating that one of the intrinsic gradient networks is... belief propagation. Rolfe’s earlier MS thesis has a dendritic + columnar model for sum-product BP. Once can do BP itself, gradient of BP is easy. Comes full circle with
@dileeplearning’s comments on the brain GD issue?1 reply 0 proslijeđenih tweetova 4 korisnika označavaju da im se sviđa -
Odgovor korisnicima @AdamMarblestone @tyrell_turing i sljedećem broju korisnika:
Adam, do you have a link to his MS thesis?
1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđa -
Odgovor korisnicima @dileeplearning @tyrell_turing i sljedećem broju korisnika:0 proslijeđenih tweetova 4 korisnika označavaju da im se sviđa
(With these bits he basically sets the stage for 6 years later saying BP is an “intrinsic gradient“ system and then generalized that concept to other dynamics like specific kinds of RNNs...)pic.twitter.com/dpQpuQwwkP
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.