About context formation...
Well, my rather vague idea was to start with a very small rule set, that didn't need to be partitioned, and evolve rule-sets by statistical correlation (what tends to get used with what). As new rules are added, at some point clusters would need to separate (for efficiency). I suppose this could all be done with activation levels, but that's not the way I tend to think of it.
I think this is essentially correct ... however, it should be noted that probabilistic inference (e.g. analogical inference) can be used to fill in gaps where observed statistical correlations don't exist... -- Ben G ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?list_id=303
