Considering that random forests have many layers and beat deep learning in most applications, maybe we just need to rebrand them as deep forests and they'll be the next big thing.
-
Random forests are just KNNs with fancy layers of metrics like likelihood, coated with methodological toppings like ‘entropy’ and ‘KL divergence’; and if it still doesn’t taste good, sprinkle it with ‘ensembles’. All of ML is essentially KNN. How about “Deep kNN?”
-
-
Interesting — the mechanism used to generate the virtual instances is key here because ideally it should bridge the gap between the input space and the label space.
-
Or representation learning, in deep learning terminology
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.