Gradient descent is hugely controversial in neuroscience. See the ultimate megathread: https://treeverse.app/view/1hX6Xm0w
Prikaži ovu nit
-
Where would you say the controversy comes from? More or less controversial then other purely theoretical neuroscience that don't (afaik) have supporting empirical evidence?
Thing is that the people arguing pro GD (e.g. me) are far more convinced about it than those of other theories. The correlation argument I am making requires just local linearity and under that assumption becomes provable. Hence, to us, it is not really a theory.
-
-
"provable under assumption" without empirical evidence sure sounds like a theory to me but ymmv
-
there is obviously experimental evidence. In countless systems weights/ activities change into the right direction. There must be hundreds if not thousands of papers.
- Još 7 drugih odgovora
Novi razgovor -
-
-
Nah, the brain solves non-convex learning problems offline during sleep with basinhopping. You experience it as dreams.
-
Maybe for certain problems. E.g. see Fig 4 here: https://papers.nips.cc/paper/2423-probabilistic-inference-in-human-sensorimotor-processing.pdf …
Kraj razgovora
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.