[yoodenvranx]

> there maybe only a few dozen instances of supervised adult instruction per day

There might be only a few dozen instances but I think each instance has a lasting effect which makes up for this.

If you scold a child for something stupid it did then it will remember this for a long-ish time. Same for teaching him things or correcting stuff.

I guess you show the child some correct behaviour at a few instances and this is then used internally as a guideline for selflearning.

[gracenotes]

That is a great point. Talking about supervised vs unsupervised vs reinforcement learning is most straightforward with tasks like language learning, audio processing, image processing, and playing discrete games. It is possible to see broad similarities between deep learning approaches and human cognition for several of these tasks. But when you start getting into tasks like the formation of narrative identity, things get very complicated.

Maybe one major difference between playing a game and forming a personality is that these early important interactions don't just adjust wirings in the cerebral cortex, the part of the brain most responsible for general intelligence. It goes straight to our emotional memory bank in the limbic system, which is all about learning an incredibly important objective function: to survive. But very high level features formed by unsupervised learning can do this, not just reptilian predator detection routines. Being scolded or corrected can have a powerful effect on future motivation. Suffice to say, artificial intelligences don't currently worry about this.