BUCKLE: a model of unobserved cause learning.

Dealing with alternative causes is necessary to avoid making inaccurate causal inferences from covariation data. However, information about alternative causes is frequently unavailable, rendering them unobserved. The current article reviews the way in which current learning models deal, or could deal, with unobserved causes. A new model of causal learning, BUCKLE (bidirectional unobserved cause learning) extends existing models of causal learning by dynamically inferring information about unobserved, alternative causes. During the course of causal learning, BUCKLE continually computes the probability that an unobserved cause is present during a given observation and then uses the results of these inferences to learn the causal strengths of the unobserved as well as observed causes. The current results demonstrate that BUCKLE provides a better explanation of people's causal learning than the existing models.

[1]  Michael R. Waldmann,et al.  Combining Versus Analyzing Multiple Causes: How Domain Assumptions and Task Context Affect Integration Rules , 2007, Cogn. Sci..

[2]  Norman H. Anderson,et al.  Contributions to information integration theory , 1991 .

[3]  Robert A. Wilson.  Causality in the Mind: Estimating Contextual and Conjunctive Causal Power , 2006 .

[4]  Controlling for Causally Relevant Third Variables , 2003, The Journal of general psychology.

[5]  P. White.  Causal attribution from covariation information: the evidential evaluation model , 2002 .

[6]  R. Rescorla.  A theory of pavlovian conditioning: The effectiveness of reinforcement and non-reinforcement , 1972 .

[7]  David R. Shanks,et al.  Effects of Trial Order on Contingency Judgments: A Comparison of Associative and Probabilistic Contrast Accounts , 1998 .

[8]  Douglas L Medin,et al.  The Psychology of Learning and Motivation: Volume 30 , 1993 .

[9]  E. E. Jones.  Attribution: Perceiving the Causes of Behavior , 1987 .

[10]  D R Shanks,et al.  Selectional processes in causality judgment , 1989, Memory & cognition.

[11]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[12]  P. Cheng,et al.  Covariation in natural causal induction. , 1992, Psychological review.

[13]  Jooyong Park,et al.  A Causal-Power Theory of Focal Sets , 1996 .

[14]  P. Cheng,et al.  From covariation to causation: a test of the assumption of causal power. , 2003, Journal of experimental psychology. Learning, memory, and cognition.

[15]  H. M. Jenkins,et al.  JUDGMENT OF CONTINGENCY BETWEEN RESPONSES AND OUTCOMES. , 1965, Psychological monographs.

[16]  D. Kirsh,et al.  Proceedings of the 25th annual conference of the Cognitive Science Society , 2003 .

[17]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[18]  L. Schulz,et al.  God does not play dice: causal determinism and preschoolers' causal inferences. , 2006, Child development.

[19]  E. H. Simpson,et al.  The Interpretation of Interaction in Contingency Tables , 1951 .

[20]  P. Cheng.  From covariation to causation: A causal power theory. , 1997 .

[21]  Thomas L. Griffiths,et al.  Dynamical Causal Learning , 2002, NIPS.

[22]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[23]  Barbara A. Spellman,et al.  Acting as Intuitive Scientists: Contingency Judgments Are Made While Controlling for Alternative Potential Causes , 1996 .

[24]  P. Cheng,et al.  Assessing interactive causal influence. , 2004, Psychological review.

[25]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[26]  H. Kelley.  Attribution in social interaction. , 1987 .

[27]  W. Ahn,et al.  The meaning and computation of causal power: Comment on Cheng and Novick and Cheng , 2005 .

[28]  V. Deved,et al.  Proceedings of the 24th IASTED international conference on Artificial intelligence and applications , 2006 .

[29]  M. Waldmann,et al.  Inferences about unobserved causes in human contingency learning , 2007, Quarterly journal of experimental psychology.

[30]  G. Lupyan.  Confounded: Causal Inference and the Requirement of Independence , 2005 .

[31]  K. Holyoak,et al.  Induction of category distributions: a framework for classification learning. , 1984, Journal of experimental psychology. Learning, memory, and cognition.

[32]  Michael R. Waldmann,et al.  Estimating causal strength: the role of structural knowledge and processing effort , 2001, Cognition.

[33]  Christian C. Luhmann,et al.  Evaluating the Causal Role of Unobserved Variables , 2003 .

[34]  H. Simon,et al.  Cognition and explanation , 1998 .

[35]  David R. Shanks,et al.  Acquisition functions in contingency judgment , 1987 .

[36]  John R. Anderson,et al.  Causal inferences as perceptual judgments , 1995, Memory & cognition.

[37]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[38]  D. Shanks.  Is Human Learning Rational? , 1995, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[39]  Johanna D. Moore,et al.  Proceedings of the 28th Annual Conference of the Cognitive Science Society , 2005 .

[40]  Jonathan D. Nelson.  Finding useful questions: on Bayesian diagnosticity, probability, impact, and information gain. , 2005, Psychological review.

[41]  W. Ahn,et al.  The meaning and computation of causal power: comment on Cheng (1997) and Novick and Cheng (2004). , 2005, Psychological review.

[42]  D. Danks.  Equilibria of the Rescorla--Wagner model , 2003 .

[43]  Joshua B. Tenenbaum,et al.  Inferring causal networks from observations and interventions , 2003, Cogn. Sci..

[44]  J. Tenenbaum,et al.  Structure and strength in causal induction , 2005, Cognitive Psychology.

[45]  U. Fayyad,et al.  Scaling EM (Expectation Maximization) Clustering to Large Databases , 1998 .

[46]  R. Sternberg,et al.  Evaluation of evidence in causal inference. , 1981 .

[47]  Robert Hooke,et al.  `` Direct Search'' Solution of Numerical and Statistical Problems , 1961, JACM.