Manfred comments on Open Problems Related to Solomonoff Induction - Less Wrong

27 Post author: Wei_Dai 06 June 2012 12:26AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (102)

You are viewing a single comment's thread. Show more comments above.

Comment author: Manfred 06 June 2012 07:31:24PM *  1 point [-]

That gives you a probability inversely proportional to the integral of e^-(the description length) of each number from 0 to infinity. Complexity grows like log(n)-ish. It's an improper prior.

So I agree with Adele that this may be a modus tollens / modus ponens moment.