Hacker News Reader

> Well obviously! A machine can't train itself!

In some cases it can. That's what unsupervised learning is.

See that's sort of what I thought but now I'm being told it was silly to expect that. ¯\_(ツ)_/¯

one expert in ML told me once: unsupervised ML is a myth. I tend to believe him.

It's better to say that unsupervised ML is merely indirectly supervised ML.

Wasn't there a second version of AlphaGo that was trained only by playing against itself without external input and turned out to be even better than the first version that was trained with external input?

Isn't that unsupervised learning?

You have ground truth on the result: one agent won the game.

With voice recognition, that's a lot more vague and human supervision is helpful.

the rules of the game, and the output from winning, is supervision.

Reply on news.ycombinator.com