Proceedings

Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning

Download BibTeX Cite

Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Cognitive Models. Pages 568-572.

© 1989 International Joint Conferences on Artificial Intelligence

Abstract

A neural net system called "Conposit" is described. Conposit performs rule-based manipulation of very short term, complex symbolic data structures. This paper concentrates on a simulated version of Conposit that embodies core aspects of JohnsonLaird's mental model theory of syllogistic reasoning. This Conposit version is not intended to be a psychological theory, but rather to act as a test and demonstration of the power and flexibility of Conposit's unusual connectionist techniques for encoding the structure of data.

  1. Bamden, J.A. (1984). On short-term information pro- cessing in connectionist theories. Cognition and Brain Theory, 7 (1), pp.25-59.
  2. Bamden, J.A. (1988a). The right of free association: relative-position encoding for connectionist data structures. Procs. lOth Annual Conf of the Cogni- tive Science Soc.
  3. Hillsdale, N.J.: Lawrence Erl- baum.
  4. Bamden, J.A. (1988b). Conposit, a neural net system for high-level symbolic processing: the register- machine level. Memoranda in Computer and Cog- mttve Science, MCCS-88-145, Computing Research Laboratory, New Mexico State Univer- sity. Modified version to appear in J.A. Bamden & J.B. Pollack (Eds), Advances in Connectionist and Neural Computation Theory, Vol. 1, Norwood, N.J.: Ablex.
  5. Fodor, J.A. & Pylyshyn, Z.W. (1988). Connectionism and cognitive architecture: a critical analysis. In S. Pinker & J. Mehler (Eds.), Connections and sym- bols, Cambridge, Mass.: MIT Press.
  6. Johnson-Laird, P.N. & Bara, B.G. (1984). Syllogistic inference. Cognition, 16 (1), pp.l-61.
  7. Shastri, L. & Ajjanagadde, V. (1989). A connectionist system for rule-based reasoning with multi-place predicates and variables. Report MS-CIS-8905, Computer and Information Science Dept, Univer- sity of Pennsylvania.
  8. Srinivas, K. & Bamden, J.A. (1989). Temporal-winner- take-all networks for arbitrary selection in connec- tionist and neural networks. Manuscript for poster at 1st Int. Joint Conf on Neural Networks, 1989.
  9. Touretzky, D.S. & Hinton, G.E. (1988). A distributed connectionist production system. Cognitive Sci- ence, 12 (3), pp.423-466.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards