From: "Ben Goertzel" <[EMAIL PROTECTED]> >You mention > >1) generalization >2) graded/smooth response > >as advantages of connectionist systems > >But of course, there is a vast amount of work on inductive and abductive >reasoning (i.e. generalization) in logic-based systems, and on uncertain >logics (which provide graded/smooth response quantified by real number >values). So even purely logic-based systems can provide both >generalization and graded/smooth response.
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... >There are nodes and links in Novamente. Let's say you have Novamente >hooked up to a camera eye with greyscale output, and the output of pixel >(100,200) has intensity 30% of maximum at time 12:30 PM March 17 2004. >Then we have a relationship in Novamente that we symbolize as > >ExampleLink := > >atTime > ( > ExecutionLink PixelIntensity (100,200) .3 , > 12:30 PM March 17 2004 > ) > >Here for instance > >* 100 and 200 and .3 are NumberNodes >* 12:30 PM March 17 2004 is a TimeNode >* PixelIntensity is a SchemaNode (indicating a function that takes input >and output >* atTime is a PredicateNode >* the (,) notation indicates a ListLink > >Let's say Novamente then represents a circle as a certain pattern among >PixelIntensity values (expressed as a complex PredicateNode involving >combinatory logic operators) > >Let's say it then generalized from this a more abstract mathematical >notion of a circle. > >Is this "symbolic"? In what sense? Patterns are being built up based >on raw perceptual inputs, much as they would be in a neural network. >It's using a logical formalism --- probabilistic combinatory term logic >-- instead of pseudo-neural operators... But so what? Again, if you used a Bayesian network to do this then it is in fact *VERY* similar to a neural network. But you can't do this with binary-valued logic (combinatory or predicate logic included). >I find that the symbolic/subsymbolic distinction is often misused. In a >complex cognitive system like Novamente (wants to be ;), there are both >symbolic and subsymbolic aspects, but it's hard to draw the line between >the two. > >Peirce, in his semiotics, drew a crisp distinction between icons, >indices and symbols, but he also understood cognitive uncertainty, and >he recognized that a given mental form could share aspects of all these >different levels of reference. This is certainly true within Novamente. 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? YKY ____________________________________________________________ Find what you are looking for with the Lycos Yellow Pages http://r.lycos.com/r/yp_emailfooter/http://yellowpages.lycos.com/default.asp?SRC=lycos10 ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
