> I just put demos of NARS 4.2 (a Java version and a Prolog version) and > several recent papers at > http://www.cogsci.indiana.edu/farg/peiwang/papers.html. > > Comments are welcome. > > Pei
Hello =) I just took a brief look at your web site and demos. It's good that you have probably the only AGI model that has a demo =) 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. 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. 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? 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]
