From: Michael Anissimov (anissimov@intelligence.org)
Date: Fri Sep 16 2005 - 14:01:43 MDT
Michael Vassar wrote:
> Does anyone know of a plausible explanation for the general dominance
> of statistical inference over Bayesian probablistic inference, both
> presently and historically?
One possible reason would be that gathering priors is a hassle, i.e.,
requires actual experimentation and data gathering. It's easier for
there to be an objectively correct way to approach any inference
problem, irrespective of prior knowledge bases. This "one objectively
correct way" also jives well with Newtonian physics and a clockwork
universe, where subjective differences in inference procedures are
equated with irrational bias.
-- Michael Anissimov http://intelligence.org/ Advocacy Director, Singularity Institute for Artificial Intelligence
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT