Proceedings

Sequences of Mechanisms for Causal Reasoning in Artificial Intelligence

Download BibTeX Cite

Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 839-844.

© 2013 International Joint Conferences on Artificial Intelligence

Abstract

We present a new approach to token-level causal reasoning that we call Sequences Of Mechanisms (SoMs), which models causality as a dynamic sequence of active mechanisms that chain together to propagate causal influence through time. We motivate this approach by using examples from AI and robotics and show why existing approaches are inadequate. We present an algorithm for causal reasoning based on SoMs, which takes as input a knowledge base of first-order mechanisms and a set of observations, and it hypothesizes which mechanisms are active at what time. We show empirically that our algorithm produces plausible causal explanations of simulated observations generated from a causal model. We argue that the SoMs approach is qualitatively closer to the human causal reasoning process, for example, it will only include relevant variables in explanations. We present new insights about causal reasoning that become apparent with this view. One such insight is that observation and manipulation do not commute in causal models, a fact which we show to be a generalization of the Equilibration-Manipulation Commutability of [Dash(2005)].

  1. Dash(2005Denver Dash. Restructuring dynamic causal systems in equilibrium. In Robert G. Cowell and Zoubin Ghahramani, editors, Proceedings of the Tenth Interna- tional Workshop on Artificial Intelligence and Statistics (AIStats 2005). Society for Artificial Intelligence and Statistics, 2005.
  2. Davidson(1967)
  3. D. Davidson. Causal relations. The Jour- nal of Philosophy, 64(21):691-703, 1967.
  4. Eells(1991)
  5. Ellery Eells. Probabilistic Causality. CUP, 1991.
  6. Getoor and Taskar(2007)]
  7. Lise Getoor and Ben Taskar, ed- itors. Introduction to Statistical Relational Learning. Adaptive Computation and Machine Learning. The MIT Press, 2007.
  8. I.J. Good. A causal calculus. British Journal of Philosophy of Science, pages 305-318, 1961.
  9. Trygve Haavelmo. The statistical impli- cations of a system of simultaneous equations. Econo- metrica, 11(1):1-12, January 1943.
  10. Halpern and Pearl(2001)]
  11. Joseph Halpern and Judea Pearl. Causes and explanations: A structural-model approach -part 1: Causes. In Proceedings of the Seventeenth Conference Annual Conference on Uncertainty in Arti- ficial Intelligence (UAI-01), pages 194-202, San Fran- cisco, CA, 2001.
  12. Morgan Kaufmann. [Halpern and Pearl(2005)]
  13. Joseph Y. Halpern and Judea Pearl. Causes and explanations: A structural-model ap- proach. part ii: Explanations. The British Journal for the Philosophy of Science, 56(4):889-911, December 2005. IJCAI
  14. Hitchcock(1995)
  15. ChristopherRead Hitchcock. The mishap at reichenbach fall: Singular vs. general causation. Philosophical Studies, 78:257-291, 1995.
  16. Kleinberg(2012)]
  17. Samantha Kleinberg. Causality, Proba- bility, and Time. 2012.
  18. Pearl(2000)] Judea Pearl. Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge, UK, 2000.
  19. Peng and Reggia(1986)]
  20. Yun Peng and James A. Reggia. Plausibility of Diagnostic Hypotheses: The Nature of Simplicity. In Proceedings of the 5th National Confer- ence on AI (AAAI-86), pages 140-145, 1986.
  21. Herbert A. Simon. Spurious correlation: A causal interpretation. Journal of the American Statisti- cal Association, 49(267):467-479, September 1954.
  22. Spirtes et al.(2000)
  23. Spirtes, Glymour, and Scheines] Peter Spirtes, Clark Glymour, and Richard Scheines. Cau- sation, Prediction, and Search. The MIT Press, Cambridge, MA, second edition, 2000.
  24. Strotz and Wold(1960)]
  25. Robert H. Strotz and H.O.A. Wold. Recursive vs. nonrecursive systems: An attempt at syn- thesis; Part I of a triptych on causal chain systems. Econometrica, 28(2):417-427, April 1960.
  26. Vennekens et al.(2009)Vennekens, Denecker, and Bruynooghe] Joost Vennekens, Marc Denecker, and Maurice Bruynooghe. Cp-logic: A language of causal proba- bilistic events and its relation to logic programming. Theory and Practice of Logic Programming, 9(3): 245-308, 2009.
  27. Vennekens et al.(2010)Vennekens, Bruynooghe, and Denecker] Joost Vennekens, Maurice Bruynooghe, and Marc De- necker. Embracing events in causal modelling: Interventions and counterfactuals in cp-logic. In The 12th European Conference on Logics in Artificial Intelligence (JELIA-2010, pages 313-325, 2010.

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

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