People who criticize machine learning for being just function approximation forget that everything is a function.
-
not everything.. the very thing that AI is trying to emulate is not...
#intelligence
-
-
You can make a function such as f(percept)=action, but you're just curve-fitting, rather than explaining why the agent acts in that way. Perhaps "schemas" are missing? IMO Knowing the answer is one thing, generalizing it to the correct settings is another.
-
Can’t we fit the function of why?
Keskustelun loppu
Uusi keskustelu -
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.