On 11/12/2012 20:19, Matt Mahoney wrote:
On Tue, Dec 11, 2012 at 6:25 PM, Tim Tyler <[email protected]> wrote:
"Differences between Kolmogorov Complexity and Solomonoff Probability [...]"
- http://agi-conference.org/2012/wp-content/uploads/2012/12/paper_7.pdf
It's Occam's razor refuted :-)
Not really. Both formalize Occam's Razor. Kolmogorov complexity is an
approximation of Solomonoff induction (shortest program M vs. average
weighted by 2^-|M|), which is valid because the shortest M dominates
the average.
Occam's razor says to prefer the shortest explanation. However, the insight
here is that the
shortest explanation might result in predictions that are *less* likely than
the predictions of
longer ones, *if* the latter are sufficiently numerous. It seems more like a
refutation than
anything else to me. Of course the ideas are similar - in much the same way
that Einstein's
ideas were similar to Newton's ;-)
--
__________
|im |yler http://timtyler.org/ [email protected] Remove lock to reply.
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com
