[gracenotes]

Interesting. I have heard the opposite of this.

Supervised learning may be how it looks from the outside, but consider that out of the >6,570,0000 waking seconds of a child's life up to age 5, there maybe only a few dozen instances of supervised adult instruction per day. Besides those, what do neurons do the remaining 99.99% of the time?

Part of the problem might be that comparing supervised and unsupervised learning 'effectiveness' is a bit apples-and-oranges. Their effect together is highly collaborative. Children have to develop abstractions on their own before you can supervise them on those abstractions. It is probably fair to say that a key part of human general intelligence is creating high-level representations of low-level stimuli. It might also be fair to say that this is what the brain is doing 100% of the time.

So if I may hand wave a little: while supervised learning can make a child better maximize objectives on those high-level representations (objectives they may be aware of through unsupervised observation), for the most part it does not fundamentally change the structure of those things in the child's brain. This makes unsupervised learning almost all of the cake to me.

My post has the caveat that children undergo a lot of other objective-based learning besides explicit instruction from adults, and all of this maps only fuzzily to supervised vs unsupervised learning in AI, which is the issue from the submitted post.

[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.

[lukeschlather]

> Supervised learning may be how it looks from the outside, but consider that out of the >6,570,0000 waking seconds of a child's life up to age 5, there maybe only a few dozen instances of supervised adult instruction per day. Besides those, what do neurons do the remaining 99.99% of the time?

This seems like a really facile analysis. For example, if I read a child a storybook, I'm deliberately providing several signals every second. That's a "single instance" but I've effectively provided a lot of training information. At least enough to keep a child's mind busy for 3600 seconds.