HI,
> If you explain to me what non-logic based reprsentation you prefer to
> use to represent a particular piece of knowledge, I can almost surely
What if you don't yet know which piece of knowledge you have to
represent? And that there are no clear specs, and the requirements
change constantly?
That is what learning is for; and there are robust learning mechanisms
corresponding to the prob. logic knowledge representation.
I was just making a point about representation; learning is a larger story...
Do you know any AI rewriting the code base (whether at SEXPR or FPGA
gate level)?
Steve Omohundro's prototype AI system (see his website, Self-Aware
Systems) reportedly works via self-modification. My Novamente system
is intended to eventually rewrite its codebase but we are not yet up
to that point.
How does one implement an efficient Kolmogorov predictor
in FPGA gates, given just the signal sequence to predict? How would
such a predictor deal with noise in the input?
I could answer that question but it doesn't have much to do with AGI,
in my view. One answer lies in Hugo de Garis's work evolving neural
nets using FPGAs. The same sorta thing could be done with logic-based
representations instead of NN's. Evolutionary learning is a
well-tested and robust approach to sequence prediction which I have
used for that purpose many times.
There must have been some recent progress in practical AI at the
architecture level. Since this is not my field, I would welcome pointers.
E.g. is there any trends in what DARPA Grand Challenge winners are using?
The Grand Challenge stuff (having to do with automated vehicle
control) has little to do with AGI, that is a classic case of narrow
AI. What they are using tells us very little about AGI.
-- Ben
-------
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
