--- On Sat, 10/25/08, Mark Waser <[EMAIL PROTECTED]> wrote: > > AIXI says that a perfect solution is not computable. However, a very > > general principle of both scientific research and machine learning is to > > favor simple hypotheses over complex ones. AIXI justifies these practices > > in a formal way. It also says we can stop looking for a universal > > solution, which I think is important. It justifies our current ad-hoc > > approach to problem solving -- we have no choice. > > Excellent. Thank you. Another good point to be pinned > (since a number of people frequently go around and around on it). > > Is there anything else that it tells us that is useful and > not a distraction?
The fact that Occam's Razor works in the real world suggests that the physics of the universe is computable. Otherwise AIXI would not apply. > - - - - - - - - - - - - - - > Also, since you invoked the two in the same sentence as if > they were different things . . . . > > What is the distinction between scientific research and machine learning > (other than who performs it, of course). Or, re-phrased, what is the > difference between a machine doing scientific research and > a machine that is simply learning? > > <I'd love to hear everybody chiming in on that last question> Scientists choose experiments to maximize information gain. There is no reason that machine learning algorithms couldn't do this, but often they don't. -- Matt Mahoney, [EMAIL PROTECTED] ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=117534816-b15a34 Powered by Listbox: http://www.listbox.com
