I think this is a weird phrasing. You can have an unsupervised learning algorithm that leads to representations that are better for downstream RL or supervised tasks. The purpose of the unsupervised alg is indeed beteer downstream performance, but the alg is still unsupervised.
-
-
-
yes, that is my point that it is weird phrasing. you are a tiger and you just attached a rhino and didn't kill it. now, you are watching the rhino, without "labeled data". why? to build a better model *that enables you to act better in the future attack*.
- Još 4 druga odgovora
Novi razgovor -
-
-
The thing is, episodic memory just snapshots sequences of events. You remember landmarks and associations of sensory experiences just because they co-occurred. I call that one-shot learning unsupervised, regardless of whether later recall is useful.
-
Although a counterpoint is that a sense of novelty or familiarity can still "supervise", or gate, this type of rapid associative learning. And later stages of selective consolidation and/or recall can also provide filtering.
Kraj razgovora
Novi razgovor -
-
-
I tend to agree with this...a constant search for even more parsimoneous, more faithful simplifications of the environment to optimize behavioral choices
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
I find any other framing questionable.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
I’d go for the opposite. Most biological learning is either unsupervised- during development- or reinforcement learning. Animals rarely need labeled input.
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.