| D. Hofstadter, "Artificial Intelligence: Subcognition as Computation", Indiana University Computer Science Department Technical Report No. 132, November 1982. |
....is no central manipulator, no central program. There is simply a vast collection of teams patterns of neural firings that, like teams of ants, trigger other patterns of neural firings. We feel those symbols churning within ourselves in somewhat the same way we feel our stomach churning. (Hofstadter, 1983, p. 279) This appears to be a serious case of Formicidae in machina: ants in the stomach of the ghost in the machine. 42 Connectionism and Cognitive Architecture Explicitness of rules According to McClelland, Feldman, Adelson, Bower, and McDermott (1986) Connectionist models are ....
Hofstadter, D.R. (1983) Artificial intelligence: Sub-cognition as computation. In F. Machlup & U. Mansfield, The Study of Information: Interdisciplinary Messages, New York, N.Y., John Wiley & Sons.
....(shared with Gentnet) we find our work to be conceptually somewhat distant from Winston s work. especially insofar as his implementation employs a strictly top.down deterministic control structure. Our arguments against such a control structure are put forth by Hofstadter (see Hofstadter:WHO, Hofstadter:SUB) The work on language and memory by the Schank group at Yale has always been concerned with deep issues of semantics. and gradually its focus has become the modeling of memory. Several people in this group have done very significant work on the structure of memory: Schank. Abelson, Kolodner, ....
D. Hofstadter, "Artificial Intelligence: Subcognition as Computation", Indiana University Computer Science Department Technical Report No. 132, November 1982.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC