Path: utzoo!attcan!uunet!seismo!sundc!pitstop!sun!decwrl!ucbvax!techunix.BITNET!dario
From: dario@techunix.BITNET (Dario Ringach)
Newsgroups: comp.ai
Subject: Valiant's Learning Model
Keywords: Computational Learning Theory
Message-ID: <6083@techunix.BITNET>
Date: 6 Nov 88 06:55:45 GMT
Sender: daemon@ucbvax.BERKELEY.EDU
Organization: Technion - Israel Inst. Tech., Haifa Israel
Lines: 13

Is it fair to assume a constant probabilistic distribution Px on space
X during the learning process?  I mean a *good* teacher would draw
points of X so as to minimize the error between the current hypothesis
and the concept to be learnt , so that the distribution Px could
change after presenting each sample (i.e. Px(n) is now a stochastic
process).  Are these two models equivalent in the sense that they can
learn the same classes of concepts?

Has anyone attempted to approach learning as a discrete time Markov
process on the hypothesis space H?  For instance at any time k let
h1=h(k) be the current hypothesis obviously there is defined for any
h2 in H a transition probability P(h(h+1)=h2|h(k)=h1) that depends
on the probability distribution Px and the learning algorithm A.