Re: Optimal Prediction

From: Juergen Schmidhuber <juergen.domain.name.hidden>
Date: Thu, 28 Mar 2002 18:09:14 +0100

Bill Jefferys wrote:

> It's pointless wasting my time on this. As both Russell and I pointed
> out, this is a standard example that is cited by people who are
> knowledgeable about the AP. Either you have a different definition of
> predictive power than the rest of us do, or you don't understand
> Hoyle's very clearly written paper. In either case, it would be
> foolish of me to continue the thread.
>
> Goodbye. <plonk>
>
> Bill
>
>"Don't try to teach a pig to sing. It wastes your time and annoys the pig."


Predictive power is measurable by standard concepts of probability
theory
and complexity theory. You may choose to ignore this, but don't include
all those who don't among "the rest of us".

Write down all assumptions, derive the consequences, and observe that
the
AP _by itself_ cannot predict anything nontrivial.

Fortunately Hoyle was more careful than some who cite him - he just
wrote: "the results...were obtained subject to certain assumptions
...have not been demonstrated in a manner free from all doubt.
Nevertheless, the number of assumptions made was much less
than the number of results obtained."

Thus he informally invoked Occam's razor: find short descriptions that
explain a lot. Occam's razor is not the AP. It is formally treated by
the theory of inductive inference. Although this theory is at the heart
of what physicists are doing, some of them are not yet fully aware of
it.

Juergen (will be out of town for a while)
Received on Thu Mar 28 2002 - 09:15:09 PST