On Fri, Jul 9, 2010 at 8:38 AM, Matt Mahoney <matmaho...@yahoo.com> wrote:
> Ben Goertzel wrote: >> > Secondly, since it cannot be computed it is useless. Third, it is not >> the sort of thing that is useful for AGI in the first place. >> > > > I agree with these two statements > > The principle of Solomonoff induction can be applied to computable subsets > of the (infinite) hypothesis space. For example, if you are using a neural > network to make predictions, the principle says to use the smallest network > that computes the past training data. > Yes, of course various versions of Occam's Razor are useful in practice, and we use an Occam bias in MOSES inside OpenCog for example.... But as you know, these are not exactly the same as Solomonoff Induction, though they're based on the same idea... -- Ben ------------------------------------------- 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=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
