Scott Aaronson's (long) "Why Philosophers Should Care About Computational Complexity" essay is great. http://www.scottaaronson.com/papers/philos.pdf …
@narayanarjun I agree with its thrust and I agree that PAC is suggestive. But Bayesian reasoning seems more helpful.
-
-
@narayanarjun And I wish 7.2 had been longer... It ended just as it got interesting.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@patrickc I think ch 7 is just a start (which is why it's so short). I agree that Bayesian reasoning seems promising, and I'd love to [1/2]Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@patrickc see a good Bayesian learning theory treatment. But most "information criterion" requirements I've seen are usually added in. [2/2] -
@patrickc so PAC is the best start I can think of. But is not conclusive. This is probably the most open of the problems listed by Aaronson.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.