@ughaibu,
ughaibu;149795 wrote:One of Chaitin's incompleteness theorems uses an equation which has either an infinite number of solutions or a finite number of solutions, which of these is the case changes purely randomly with the change in one variable of the equation. This is a matter of mathematical proof, it is not a statement of belief, like "we haven't figured out the pattern to yet or don't have enough information about". To maintain a belief after you're aware that it has been proven false, is irrational.
like I said any indeterministic FSM has an equivalent deterministic one so there's no reason to think that any local "random" phenomena is not being deterministically controlled
---------- Post added 04-08-2010 at 10:06 PM ----------
In this article we present an algorithm that learns to predict non-deterministically generated strings. The problem of learning to predict non-deterministically generated strings was raised by Dietterich and Michalski (1986). While their objective was to give heuristic techniques that could be used to rapidly and effectively learn to predict a somewhat limited class of strings, our objective is to give an algorithm which, though impractical, is capable of learning to predict a very general class. Our algorithm is meant to provide a general framework within which heuristic techniques can be effectively employed.
Given a sequence of events (or ob]ects), each 'characterized by a set of attributes, the problem considered is to discover a rule characterizing the sequence and able to predict a plausible sequence continuation. The rule, called a sequence-generating rule, is nondeterministic in the sense that it does not necessarily tell exactly which etent must appear next in the sequence, but rather, defines a set of plausible next eents.
apparently Dietterich and Michalski think they can "predict" these non-determinacally generated strings