Unsupervised learning can learn things humans can’t supervise because there’s structure in the world that you need deeper understanding to predict accurately. For example, to predict how characters in a story will behave, you have to have some kind of understanding in some sense of how those characters think, even if their thoughts are never explicitly visible.
Unfortunately, this understanding only has to be structured in a way that makes reading off the actual unsupervised targets (i.e next observation) easy.
Unsupervised learning can learn things humans can’t supervise because there’s structure in the world that you need deeper understanding to predict accurately. For example, to predict how characters in a story will behave, you have to have some kind of understanding in some sense of how those characters think, even if their thoughts are never explicitly visible.
Unfortunately, this understanding only has to be structured in a way that makes reading off the actual unsupervised targets (i.e next observation) easy.