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

  title={Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning},
  author={John A. Barnden},
A neural net system called "Conposi t " 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… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-8 of 8 references

On short-term information processing in connectionist theories

  • J. A. Barnden
  • Cognition and Brain Theory,
  • 1984
Highly Influential
4 Excerpts

Conposit, a neural net system for high-level symbolic processing: the registermachine level

  • J. A. Barnden
  • Memoranda in Computer and Cognitive Science, MCCS…
  • 1988
Highly Influential
4 Excerpts

The right of free association: relative-position encoding for connectionist data structures

  • J. A. Barnden
  • Procs. 10th Annual Conf of the Cognitive Science…
  • 1988
Highly Influential
4 Excerpts

A connectionist system for rule-based reasoning with multi-place predicates and variables

  • L. Shastri, V. Ajjanagadde
  • Report MS-CIS-8905,
  • 1989
1 Excerpt

Conncclionism and cognitive architecture: a critical analysis

  • J. A. Fodor
  • Connections and symbols,
  • 1988

Similar Papers

Loading similar papers…