At 11:40 AM +0200 4/4/02, Juergen Schmidhuber wrote:
>One has to choose priors. Exactly. To repeat the nontrivial point:
>The only choice you need to obtain Occam's razor is to restrict
>yourself to priors computable in the limit (this is not much of a
>restriction in the sense that other priors are beyond constructive
>description anyway). Then you'll automatically prefer few knobs to
>tweak, or, more generally, short descriptions of the
>observations: http://www.idsia.ch/~juergen/toesv2/
There are lots of ways to look at problems. Yours is an interesting
way to look at Ockham's razor. I believe that the way that Jim and I
look at it is also interesting. Our two ways do not have to be
exclusive, nor is one "right" and the other "wrong". Each may be
applicable in its own sphere, and each may be useful in understanding
the other.
Best wishes,
Bill
Received on Sun Apr 07 2002 - 08:10:43 PDT