Modeling commonsense rules in an inference network

  • Boon Toh Low
Neural Nets and Uncertainity II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1114)


In commonsense reasoning, conditional statements of the form “IF condition(s) THEN conclusion(s)” are the most common and important constructions. While material implication is generally used in classical logic based belief representation systems, its dual implication could be semantically too strong for expressing commonsense IF-THEN rules because not all contributing conditions of a rule can be expressed (the Qualification Problem [18]) and the negation of conclusions do not always imply the negation of the conditions. This paper studies a hybrid neural-symbolic belief representation system called Neural-Logic Belief Network (NLBN) [14] where IF-THEN rules can be more realistically captured for commonsense reasoning. Deduction of an IF-THEN rule in this formalism is considered as information flow from the condition(s) to the conclusion(s). In this system, the strength of conclusions can be modeled by using individual rule mapping functions.


inference network belief systems conditionals commonsense reasoning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ernest Wilcox Adams. Logic of Conditionals: an Application of Probability to Deductive Logic. D. Reidel, Dordrecht, 1975.Google Scholar
  2. 2.
    C. E. Alchourron, Peter Gärdenfors, and David Makinson. On the logic of theory change: Partial meet functions for contraction and revision. Journal of Symbolic Logic, 50:510–530, 1985.Google Scholar
  3. 3.
    Richard Boyd, Philip Gasper, and J. D. Trout, editors. The Philosophy of Science. MIT Press, Cambridge, Massachusetts, 1991.Google Scholar
  4. 4.
    Ronald J. Brachman and Hector J. Levesque, editors. Readings in Knowledge Representation. Morgan Kaufmann, San Mateo, California, 1985.Google Scholar
  5. 5.
    Bruce G. Buchanan and Edward H. Shortliffe. Rule-Based Expert Systems — The MYCIN Experiments of the Stanford Heuristic Programming Project. Addison-Wesley Publishing Company, Reading, Massachusetts, 1984.Google Scholar
  6. 6.
    Jon Doyle. A truth maintenance system. Artificial Intelligence J., 12:231–272, 1979.Google Scholar
  7. 7.
    Peter Gärdenfors. Knowledge in Flux: Modeling the Dynamics of Epistemic States. MIT Press, Cambridge, Massachusetts, 1988.Google Scholar
  8. 8.
    Peter Gärdenfors and David Makinson. Nonmonotonic inferences based on expectations. Artificial Intelligence J., 65:197–245, 1994.Google Scholar
  9. 9.
    Matehew L. Ginsberg, editor. Readings in Nonmonotonic Reasoning. Morgan Kaufmann, 1985.Google Scholar
  10. 10.
    Brian W. Kernighan and Dennis M. Ritchie. The C Programming Language. Prentice-Hall, Englewood Cliffs, New Jersey, 1978.Google Scholar
  11. 11.
    D. K. Lewis. Counterfactuals. Blackwell, Oxford, 1973.Google Scholar
  12. 12.
    Boon Toh Low. Reasoning about Beliefs: An Inference Network Approach. PhD thesis, Basser Department of Computer Science, University of Sydney, 1994.Google Scholar
  13. 13.
    Boon Toh Low. A subsumptive inference network for belief representation. In proceedings of the Third Pacific Rim International Conference on Artificial Intelligence, Beijing, 1994.Google Scholar
  14. 14.
    Boon Toh Low and Norman Y. Foo. A network formalism for commonsense reasoning. In Proceedings of the Sixteenth Australian Computer Science Conference, pages 425–434, Brisbane, 1993.Google Scholar
  15. 15.
    Boon Toh Low and Norman Y. Foo. Competitive voting semantics for neural-net decision functions. In Proceedings of the Second Singapore International Conference on Intelligent Systems, SPICIS'94, Pages 225–230, 1994.Google Scholar
  16. 16.
    Witold Lukaszewicz. Two results on default logic. In Proceedings of 9th IJCAI, pages 459–461, Los Angeles, 1985.Google Scholar
  17. 17.
    John McCarthy. Circumscription: A form of non-monotonic reasoning. Artificial Intelligence J., 13:27–39, 1980.Google Scholar
  18. 18.
    John McCarthy and Patrick J. Hayes. Some philosophical problems from the standpoint of artificial intelligence. In B. Meltxer and D. Mitchie, editors, Machine Intelligence 4, pages 463–502. Edinburgh University Press, 1969.Google Scholar
  19. 19.
    Drew McDermott. AI, logic and the frame problem. Proceedings of the Frame Problem in Artificial Intelligence Workshop, pages 105–118, 1987.Google Scholar
  20. 20.
    Donald Michie, editor. Introductory Readings in Expert Systems. Gordon and Breach, Science Publishers, New York, 1982.Google Scholar
  21. 21.
    George A. Miller. Trends and debates in cognitive psychology. Cognition, 10:215–225, 1981.Google Scholar
  22. 22.
    D. Nute. Defeasible reasoning and decision support systems. Decision Support Systems, 4:97–110, 1988.Google Scholar
  23. 23.
    R. Reiter. A logic for default reasoning. Artificial Intelligence J., 13:81–132, 1980.Google Scholar
  24. 24.
    Abdul Satta and R. Goebel. Constraint satisfaction as hypothetical reasoning. In Proceedings of AAAI'92, Cancun, Mexico, 1992. AAAI Press.Google Scholar
  25. 25.
    Jude W. Shavlik and Thomas G. Dietterich, editors. Readings in Machine Learning. Morgan Kaufmann, San Mateo, California, 1990.Google Scholar
  26. 26.
    Pei Zhuang Wang. Fuzzy Sets and Falling Shadows of Random Sets. Beijing Normal University Press, 1985.Google Scholar
  27. 27.
    Lotfi A. Zadeh. Knowledge representation in fuzzy logic. IEEE Transactions on Knowledge and Data Engineering, 1(1):89–100, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Boon Toh Low
    • 1
  1. 1.Department of Systems Engineering and Engineering ManagementThe Chinese University of Hong KongShatinHong Kong

Personalised recommendations