How does the mind arouse so many -- but not too many -- memories so quickly? Minsky's approach is the level-band theory. "The basic idea is simple: we learn by attaching agents to K-lines,but we don't attach them all with equal firmness. Instead, we make strong connections at a certain level of detail, but we make weker connections at higher and lower levels."
From this perspective, K-lines don't activate all agents equally well. Furthermore, the weakly activated agents serve as default memories that are activated (to fill a slot), but which can be easily changed. "Default assumptions embody some of our most valuable kinds of commonsense knowledge: knowing what is usual or typical."
(NB1: Level-band theory makes me think of Rosch's work on conceptual levels.)
(NB2: If agents are binary, how does level band theory work? All in connections, or is agent activity stochastic (like in a Boltzman machine or Hopfield net)?)
(NB3: Schema theory -- or, given the author, more properly frames -- is alluded to here.)
Pearl Street | Society of Mind Home Page | Dawson Home Page |