It’s a basic ML fact that there’s an infinity of laws compatible with the same observations. Which ones we believe is more a function of psychology than physics.
-
In comparing hypotheses that are consistent with observations, more constrained hypotheses will be more likely (Occam's razor), simply as a consequence of probability (since they cannot generate many other observations), rather than subjective preference.
-
-
I wrote this speculatively when I was thinking about this problem, sometimes you can get an occamian prior from a flat syntactic priorhttp://davidruescas.com/occams-razor-in-a-cellular-physics-universe/ …
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.