> To be perfectly honest, connectionist versus symbolic has always come > across as a strange dichotomy that seems to me would be a false > dichotomy as well in any reasonable model. I don't see why a reasonable > system couldn't be interpreted as either depending on how narrowly one > wanted to slice their perspective.
I can provide a concrete example to support the last sentence, but I guess most people on this list already know what I'm going to say, so I won't say it. ;-) However, the connectionist versus symbolic distinction did make sense in history --- when connectionism came back in the late 80's, what "symbolic AI" indicated at that time was indeed very different from what the connectionists want to do. I learnt several things from the connectionist versus symbolic debate, and end up mainly using the philosophy of the former, and the technique of the latter. The distinction has been blurred to an extent today, as Ben explained, so to continue the old arguments does not make sense anymore. Pei > The "distinction without a difference" aspect of it for AGI design, at > least as far as I can tell, makes the question irrelevant IMO. > > j. andrew rogers > > ------- > 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]
