Hi,
> If the system is fuzzy or Bayesian, then I agree that > smoothness of response is not a problem. With conventional > binary-valued logic, it seems the problem still exists. But > then Novamente is using a probabilistic logic which I assume > is Bayesian... The word "Bayesian" is a bit ambiguous. We use a probabilistic inference framework called "Probabilistic Term Logic," which includes Bayes' rule among many other aspects. We don't use Judea Pearl style Bayesian networks, for example. > One more aspect about connectionist systems is that any > concept is potentially *associable* with another concept. > So in the human mind butterflies are associated with > chaos theory and cats are associated with quantum mechanics, > even though these things are not directly causally related. > Can a logical/Bayesian system do the same? Yes, this is an aspect of what philosophers of logic call "intensional" inference. Novamente draws these sorts of inferences all the time, in its current working version. This is not one of the more difficult parts of creating an AGI, actually. -- Ben ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
