Astonishing - deep networks are just kernel machines, regardless of architecture: https://news.cs.washington.edu/2020/12/02/uncovering-secrets-of-the-black-box-pedro-domingos-author-of-the-master-algorithm-shines-new-light-on-the-inner-workings-of-deep-learning-models/ …
-
Doesn't every smooth function have a representation as an equivalent kernel?
-
-
every smooth function has associated constraints in terms oof the derivatives of the function. This can be used to define an RKHS.
-
Not always. Consider space of functions f with second derivatives having bounded L1 norm (ie total variation). This defines a Banach space that isn’t a Hilbert space.
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.