here’s a conjecture: biological learning is never unsupervised. Rather, its goal is to learn representations that are useful for future behavior. @AstroKatie @AToliasLab @danilobzdok
-
-
True, but the reason I would still call it "unsupervised" is because the learning algorithm itself is using only the sensory data, no other rewards or external targets, to determine the parameter updates.
-
You can break this down into a few possibilities 1) something like this, which is not simply optimizing some parsimonious/simple objective like “compression” or “reconstruction”, and whose goal is downstream task performance, but is still unsupervised: https://arxiv.org/abs/1804.00222
- Još 1 odgovor
Novi razgovor -
-
-
There were times when people called unsupervised learning self-organization. You only need input and a guiding principle. No need for labeled data.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.