> > > True. The more fundamental point is that symbols representing entities and > concepts need to be grounded with (scalar) attributes of some sort. > > How this is *implemented* is a practical matter. One important > consideration > for AGI is that data is easily retrievable by vector distance (similarity) > and that new patterns can be leaned (unlearned) incrementally. > > Peter
Again, I agree with your general point, but I'll observe that *vector distance* is only one among many ways of measuring similarity! We do use vector distance for some things in Novamente, but our more fundamental distance measure is based on what we call the "inference metric"... a different way of measuring distances that still obeys the metric space axioms, but cooperates more nicely with probabilistic inference. Somewhere in the future, there lies a general theory of AGI of which all our current attempts will be comprehensible as special cases ;) -- Ben G ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
