Re: Bayesian epistemology versus Geddesian epistemology

From: Paul Fidika (fidika@gmail.com)
Date: Sat May 28 2005 - 20:22:55 MDT


Marc Geddes wrote:
> This looks good on paper. It does superficially
> appear to be the case that deduction is just a special
> case of Bayesian reasoning.

Translation: Ok, so I said something really stupid...

> Some problems though. For one thing, there's more to
> intelligence than just calculation of probabilities -
> there is also the goal system. The thing about
> deduction is that there is more going on than just
> calculation of probabilities. There is a switch to
> descriptions of reality at higher levels of
> organization where classifications are being made that
> go beyond mere associations. This implicitly
> introduces an 'extra' ingredient over and above mere
> calculation of probabilities.

Translation: ...so now I'm going to say something
irrelevant, to change the topic.

> I wouldn't be so quick to embrace the religion of
> Bayes if I were you. Reading more widely in
> philosophy reveals that there are dissenting opinions
> as to whether the Bayesian framework really is the
> ultimate epistemology that it is touted to be. For
> instance I recommend the excellent book 'Theory and
> Reality' by leading philosopher of science
> Godfrey-Smith. He devotes a whole chapter to the
> philosophy of Bayesianism, beginning with this:
>
> 'Although Bayesian is most popular approach to solving
> these problems today, I am not in the Bayesian camp.
> Some parts of Bayesianism are undeniably powerful, but
> I would cautiously put my money on some different
> ideas. These will be introduced at the end of the
> chapter...'
>
> Go read the book...

Oh god no! Hopefully no one on this list wastes their time
doing such a thing! A word of advice: don't waste your time
with the "philosophy of science". (1) Bayes already presents a
solution to the "problem" of induction. (2) Bayes presents a
quantitative "Occam's Razor", obviating the need for determining
which hypothesis is simpler.

The applied Bayesian-statistician daily makes use of these
solutions, while the philosophers will continue to argue about
these solved problems for decades to come.

When you have the calculus of science, of what use is the
philosophy of it?



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT