A Two-Level Hybrid Architecture for Structuring Knowledge for Commonsense Reasoning

Part of the The Springer International Series In Engineering and Computer Science book series (SECS, volume 292)


In this chapter, a connectionist architecture for structuring knowledge in vague and continuous domains is proposed. The architecture is hybrid in terms of representation, and it consists of two levels: one is an inference network with nodes representing concepts and links representing rules connecting concepts, and the other is a microfeature-based replica of the first level. Based on the interaction between the concept nodes and microfeature nodes in the architecture, inferences are facilitated and knowledge not explicitly encoded in a system can be deduced via a mixture of similarity matching and rule application. The architecture is able to take account of many important desiderata of plausible commonsense reasoning, and produces sensible conclusions.


Knowledge Statement Bottom Level Horn Clause Rule Application Similarity Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    J. Anderson and E. Rosenfeld, (eds.) Neurocomputing, MIT Press, Cambridge, MA. 1988Google Scholar
  2. [2]
    L. Bookman, A Connectionist Scheme For Modeling Context, In D. Touretzky et al. eds. Proc. 1988 Connectionist Summer School, pp. 281–290. San Mateo, CA: Morgan Kaufman, 1989Google Scholar
  3. [3]
    C. Chang and R. C. Lee, Symbolic Logic and Mechanical Theorem Proving, Academic Press, San Diago, CA. 1973MATHGoogle Scholar
  4. [4]
    A. Collins and R. Michalski, The Logic of Plausible Reasoning: A Core Theory, Cognitive Science, Vol 13,No 1, pp. 1–49, 1989CrossRefGoogle Scholar
  5. [5]
    M. Derthick, Mundane reasoning by parallel constraint satisfaction, TR CMU-CS-88-182, Carnegie-Mellon University, 1988Google Scholar
  6. [6]
    D. Dubois and H. Prade, An Introduction to Possibilistic and Fuzzy Logics, in: P. Smets et al (eds.) Non-Standard Logics for Automated Reasoning, Academic Press, San Diago, CA. 1988Google Scholar
  7. [7]
    J. Feldman, Neural Representation of Conceptual Knowledge, Technical Report 189, Department of Computer Science, University of Rochester, 1986Google Scholar
  8. [8]
    L. Fu, Recognition of Semantically Incorrect Rules, Proc. IEA/AIE-90, 1990Google Scholar
  9. [9]
    S. Gallant, Connectionist Expert Systems, Communication of ACM, V.31(2), pp. 152–169,1988CrossRefGoogle Scholar
  10. [10]
    J. Gelfand, D. Handelman and S. Lane, Integrating Knowledge-based Systems and Neural Networks for Robotic Skill Acquisition, Proc. IJCAI, pp.193–198, Morgan Kaufman, San Mateo, CA. 1989Google Scholar
  11. [11]
    S. Grossberg, The Adaptive Brain, North-Holland, New York, NY. 1987Google Scholar
  12. [12]
    P.J. Hayes, In defence of logic, Proc. 5th IJCAI, pp. 559–565, Morgan Kaufman, San Mateo, CA. 1977Google Scholar
  13. [13]
    F. Hayes-Roth, D.A. Waterman and D.B. Lenat, eds. Building Expert Systems, Addison-Wesley, Reading, MA. 1983Google Scholar
  14. [14]
    J. Hendler, Marker Passing and Microfeature, Proc. 10th IJCAI, pp. 151–154, Morgan Kaufman, San Mateo, CA. 1987Google Scholar
  15. [15]
    J. Hendler, Integrating Marker Passing and Problem Solving, Lawrence Erlbaum Associates, Hillsdale, NJ. 1988.Google Scholar
  16. [16]
    K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks, Vol.2 pp. 359–366. 1989CrossRefGoogle Scholar
  17. [17]
    R. Lacher et al, Backpropagation learning in expert networks, IEEE Transactions on Neural Networks. 3, 62–72,1992.CrossRefGoogle Scholar
  18. [18]
    T. Lange and M. Dyer, Frame selection in a connectionist model, Proc. 11th Cognitive Science Conference, pp. 706–713, Lawrence Erlbaum Associates, 1989Google Scholar
  19. [19]
    H. Leonard, Principle of Reasoning. Dover, New York, NY. 1967Google Scholar
  20. [20]
    R. Michalski, Two-tiered concept meaning, inferential matching, and conceptual cohesiveness, in S. Vosniadou & J. Ortony, (eds.) Similarity and Analogical Reasoning, Cambridge University Press, New York, NY. 1989Google Scholar
  21. [21]
    M. Minsky, The Society of Mind, Simon and Schuster, New York, NY. 1985Google Scholar
  22. [22]
    M. Posner, (ed.) Foundations of Cognitive Science, MIT Press, Cambridge, MA. 1989Google Scholar
  23. [23]
    J. Pearl, Probabilistic Reasoning in Intelligent Systems, Morgan Kaufmann, San Mateo, CA. 1988Google Scholar
  24. [24]
    C. Riesbeck and R. Schank, Inside Case-based Reasoning, Lawrence Erlbaum Associate, Hillsdale, NJ. 1989Google Scholar
  25. [25]
    J. McClelland, D. Rumelhart, and the PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructures of Cognition, MIT Press, Cambridge, MA. 1986Google Scholar
  26. [26]
    G. Shafer, A Mathematical Theory of Evidence, Princeton University Press, Princeton, NJ. 1974Google Scholar
  27. [27]
    R. Sun, A discrete neural network model for conceptual representation and reasoning, Proc 11th Cognitive Science Society Conference, pp. 916–923, Erlbaum, Hillsdale, NJ. 1989 aGoogle Scholar
  28. [28]
    R. Sun, Designing inference engines based on a discrete neural network model, Proc IEA/AIE, ACM Press, New York, NY. p. 1094, 1989 bGoogle Scholar
  29. [29]
    R. Sun, Rules and Connectionism, Proc.INNC-Paris, p.545, Kluwer, Netherlands. 1990 aGoogle Scholar
  30. [30]
    R. Sun, The Discrete Neuronal Models, Proc. INNC-Paris, pp. 902–907, Kluwer, Netherlands. 1990 bGoogle Scholar
  31. [31]
    R. Sun, The Discrete Neuronal Models and the Discrete Neuronal Models, in: B. Soucek ed. Neural and Intelligent System Integration, John Wiley & Sons, New York, NY. 1991 aGoogle Scholar
  32. [32]
    R. Sun, Chunking and Connectionism, Neural Network Review, Vol. 4,No.2, pp. 76–78, 1991 bGoogle Scholar
  33. [33]
    R. Sun and D. Waltz, Neurally Inspired Massively Parallel Model of Rule-Based Reasoning, in: B. Soucek ed. Neural and Intelligent System Integration, John Wiley & Sons, New York, NY. 1991Google Scholar
  34. [34]
    R. Sun, A connectionist model of commonsense reasoning incorporating rules and similarities. Knowledge Acquisition, Vol. 4, 293–321, 1992CrossRefGoogle Scholar
  35. [35]
    R. Sun, Beyond associative memories, logics and variables in connectionist networks. Information Sciences, Vol. 70, 1993Google Scholar
  36. [36]
    D. Touretzky, The Mathematics of Inheritance. Morgan Kaufman, San Mateo, CA. 1986MATHGoogle Scholar
  37. [37]
    G. Towell, J. Shavlik, and M. Noordewier, Refinement of approximate domain theories by knowledge-based neural networks. Proc. AAAI-90, pp. 861–866. Morgan Kaufman, San Mateo, CA. 1990Google Scholar
  38. [38]
    A. Tversky, Features of Similarity, Psychological Review, 84(4), pp. 327–352, 1977CrossRefGoogle Scholar
  39. [39]
    S. Vosniadou & J. Ortony, (eds.) Similarity and Analogical Reasoning, Cambridge University Press, New York, NY. 1989Google Scholar
  40. [40]
    D. Waltz and J. Pollack, Massively Parallel Parsing, Cognitive Science, 1985Google Scholar
  41. [41]
    L. Zadeh, Fuzzy Sets, Information and Control, 8, pp. 338–353, 1965MATHCrossRefGoogle Scholar
  42. [42]
    L. Zadeh, Test-score semantics for natural languages and meaning-representation via PRUF, in: B. Rieger, (ed.) Empirical Semantics. pp. 281–349. Bochum: Brockmeyer. 1981Google Scholar
  43. [43]
    L. Zadeh, Fuzzy Logic, Computer, Vol. 21,No. 4, pp. 83–93, April 1988CrossRefGoogle Scholar
  44. [44]
    M. Waterman, An Introduction to Expert Systems. Addison-Wesley, Reading, MA. 1985Google Scholar

Copyright information

© Kluwer Academic Publishers 1995

Authors and Affiliations

  • Ron Sun
    • 1
  1. 1.Department of Computer Science College of EngineeringThe University of AlabamaTuscaloosa

Personalised recommendations