Gradient descent is hugely controversial in neuroscience. See the ultimate megathread: https://treeverse.app/view/1hX6Xm0w
Prikaži ovu nit
I’m puzzled as, surveying the landscape visible from Dunning & Kruger’s Mount Stupid, I’m not aware of an AI program that works without some kind of gradient descent (as pure solution search takes too long) which suggests biological computation will have the same limit.
-
-
But couldn't biologists argue that the reason could be that simply all AI systems share a common evolutionary basis (code written by humans) and may thus be fundamentally different.
-
I don’t see how. The problem isn’t humans, but the number of possibilities that have to be considered and anticipated. Without gradient descent, you’ve got to wait for the infinity of typewriting monkeys.
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.