> My suggestion (which applies to all AGI researchers) to assess the > merits of AGI models is to consider the following 4 points: > 1) speed > 2) approximation (=fault tolerance/robustness) > 3) flexibility > 4) adaptiveness > And it seems that speed is the limiting factor with current hardware.
Well, they are all desired, of course, but I'm afraid the first three may mean different things for different people. I fully agree with the last one. > I haven't read your technical papers yet, but I want to ask if NARS > can handle massive number of inputs and whether it is faster than > neural networks, since I think this is the limiting factor. You'll have to read my technical paper (such as http://www.cis.temple.edu/~pwang/drafts/Computation.pdf) to fully understand what I mean in the fillowing. ;-) NARS cannot be compared with NN in general, because they are designed for different purposes. They don't exactly work on the same tasks, so it is hard to say which is faster. NARS is designed to handle massive number of inputs, meaning that it will not be killed by it. However, by "to handle", it is included that some input will be ignored, or only briefly processed. Again, see the above paper. > I've heard many times that symbolic logic / probabilistic models are > faster than neural networks but I think this is mainly because > symbolic AI does not satisfy all 4 of the above requirements (the > problem being the lack of distributiveness and thus the AI is brittle). > If one requires a distributive representation then NN should be > *faster* than traditional symbolic approaches, IMO. ANy comments? I don't think the general comparision on speed between different paradigms makes much sense, sinse thay are faster on different tasks. Also, the logic/NN distinction doesn't always make sense. For example, if you say that NARS is a logic, I can show you that it is also a dynamic network. Pei > 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] > ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
