People who think AI will be solved by gradient descent need to explain how scientists make discoveries using nothing else.
-
Discoveries are a gradual process. Newton didn't discover gravity the very first moment. It was a hypothesis which he finally solved gradually, through trial and errors and updating his beliefs and internal errors. So did Einstein.
-
-
I would say more like policy gradient since he didn't have any supervision and had to solve it like a reinforcement learning problem. But yeah, human equivalent PG was definitely involved.
Kiitos. Käytämme tätä aikajanasi parantamiseen. KumoaKumoa
-
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.