A review of recent research in metareasoning and metalearning

AI Magazine

Volumn 28, Issue 1, 2007, Pages 7-16

  Anderson, Michael L ^a,b   Oates, Tim ^c  

^a MARSHALL UNIVERSITY   (United States)

^b UNIVERSITY OF MARYLAND   (United States)

^c Baltimore County   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

METACOGNITION; METALEARNING; METAREASONING;

COGNITIVE SYSTEMS; ENGINEERING RESEARCH; LEARNING SYSTEMS; METADATA;

INTELLIGENT SYSTEMS;

EID: 34247390032     PISSN: 07384602     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Review

References (77)

1. Aha, D. 1992. Generalizing from Case Studies: A Case Study. In Proceedings of the 9th International Workshop on Machine Learning, 1-10. San Francisco: Morgan Kaufmann Publishers.
2. Allenby, G. M., and Rossi, P. E. 1999. Marketing Models of Consumer Heterogeneity. Journal of Econometrics 89(1-2): 57-78.
3. Anderson, M.; Oates, T.; Chong, Y.; and Perlis, D. 2006. Enhancing Reinforcement Learning with Metacognitive Monitoring and Control for Improved Perturbation Tolerance. Journal of Experimental and Theoretical Artificial Intelligence. 18(3): 387-411.
4. Anderson, M., and Perlis, D. 2005a. Logic, Self-Awareness, and Self-Improvement: The Metacognitive Loop and the Problem of Brittleness. Journal of Logic and Computation 15(1): 21-40.
5. Anderson, M., and Perlis, D. 2005b. The Roots of Self-Awareness. Phenomenology and the Cognitive Sciences 4(3): 297-333.
6. Arkoudas, K., and Bringsjord, S. 2004. Metareasoning for Multi-Agent Epistemic Logics. In Proceedings of the Fifth International Workshop on Computational Logic in Multi-Agent Systems, Lecture Notes in Artificial Intelligence 3487, ed. João Leite and Paolo Torroni, 111-25. Berlin: Springer.
7. Bakker, B., and Heskes, T. 2003. Task Clustering and Gating for Bayesian Multitask Learning. Journal of Machine Learning Research 4(2003): 83-99.
8. Barklund, J.; Dell'acqua, P.; Costantini, S.; and Lanzarone, G. 2000. Reflection Principles in Computational Logic. Journal of Logic and Computation 10(6): 743-86.
9. Baxter, J. 2000. A Model of Inductive Bias Learning. Journal of Artificial Intelligence Research, 12: 149-198.
10. Ben-David, S., and Schuller, R. 2003. Exploiting Task Relatedness for Multiple Task Learning. In Learning Theory and Kernel Machines, Lecture Notes in Artificial Intelligence 2777, ed. B. Schölkopf and M. Warmuth, 567-80. Berlin: Springer.
11. Bensusan, H.; Giraud-Carrier, C.; and Kennedy, C. 2000. A High Order Approach to Metalearning. Paper presented at the Eleventh European Conference on Machine Learning, Workshop on Meta-learning, Barcelona, Spain, May-June.
12. Berger, J. O. 1985. Statistical Decision Theory and Bayesian Analysis. Berlin: Springer.
13. Bolander, T. 2003. Logical Theories for Agent Introspection. Ph.D. dissertation, Computer Science, Technical University of Denmark, Lyngby, Denmark.
14. Brieman, L. 1996. Bagging Predictors. Machine Learning 24(2): 123-40.
15. Brodley, C. 1994. Recursive Automatic Bias Selection for Classifier Construction. Machine Learning 20(1-2): 63-94
16. Caleiro, C.; Vigan, L.; and Basin, D. 2005. Metareasoning about Security Protocols Using Distributed Temporal Logic. In Proceedings of the Workshop on Automated Reasoning for Security Protocol Analysis, Electronic Notes In Theoretical Computer Science 125(1): 67-89.
17. Caruana, R. 1997. Multitask Learning. Machine Learning 28(1): 41-75.
18. Cicirello, V. 2003. Boosting Stochastic Problem Solvers through Online Self-Analysis of Performance. Ph.D. dissertation, Carnegie Mellon University, Technical Report CMU-RI-TR-03-27, Pittsburgh, PA.
19. Cohen, M., and Thompson, B. 2005. Metacognitive Processes for Uncertainty Handling: Connectionist Implementation of a Cognitive Model. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
20. Conitzer, V., and Sandholm, T. 2003. Definition and Complexity of Some Basic Metareasoning Problems. In Proceedings of the 18th International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers.
21. Costa, F. 2001. Combining Meta-Information Management and Reflection in an Architecture for Configurable and Reconfigurable Middleware. Ph.D. dissertation, Lancaster University, Computing Department, Lancaster, UK.
22. Costantini, S. 2002. Meta-Reasoning: A Survey. In Computational Logic: From Logic Programming into the Future: Special Volume In Honour of Bob Kowalski, ed. A. Kakas and F. Sadri. Berlin: Springer-Verlag.
23. Cox, M. 2005. Metacognition in Computation: A Selected Research Review. Artificial Intelligence 169(2): 104-41.
24. Evgeniou, T., and Pontil, M. 2004. Regularized Multitask Learning. In Proceedings of the Tenth Conference on Knowledge Discovery and Data Mining. New York: Association for Computing Machinery.
25. Finkelstein, L., and Markovitch, S. 2001. Optimal Schedules for Monitoring Anytime Algorithms. Artificial Intelligence 126(1-2): 63-108.
26. Flavell, J. H. 1979. Metacognition and Cognitive Monitoring: A New Area of Cognitive-Developmental Inquiry. American Psychologist 34(10): 906-11.
27. Flavell, J. H. 1987. Speculations about the Nature and Development of Metacognition. In Metacognition, Motivation and Understanding, ed. F. E. Weinert and R. H. Kluwe, 21-9. Hillside, New Jersey: Lawrence Erlbaum Associates.
28. Freund, Y. and Schapire, R. 1996. Experiments with a New Boosting Algorithm. In Proceedings of the Thirteenth International Conference on Machine Learning, 148-56. San Francisco: Morgan Kaufmann Publishers.
29. Friedman, J. 1997. On Bias, Variance, 0/1-Loss, and the Curse of Dimensionality. Data Mining and Knowledge Discovery 1(1): 55-77.
30. Ganek, A. G., and Corbi, T. A. 2003. The Dawning of the Autonomic Computing Era. IBM Systems Journal 42(1): 5-18.
31. Garfinkel, T., and Rosenblum, M. 2003. A Virtual Machine Introspection-Based Architecture for Intrusion Detection. In Proceedings of the Network and Distributed Systems Security Symposium. Reston, VA: Internet Society.
32. Goldman, C. V., and Zilberstein, S. 2003. Optimizing Information Exchange in Cooperative Multi-Agent Systems. In Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems. New York: Association for Computing Machinery.
33. Goldman, R.; Musliner, D.; and Krebsbach, K. 2003. Managing Online Self-Adaptation In Real-Time Environments, Lecture Notes In Computer Science, 2614, 6-23. Berlin: Springer.
34. Good, I. J. 1980. Some History of the Hierarchical Bayesian Methodology. In Bayesian Statistics II, ed. J. M. Bernardo, M. H. D. Groot, D. V. Lindley, and A. F. M. Smith. Oxford: Oxford University Press.
35. Hansen E., and Zilberstein, S. 2001. Monitoring and Control of Anytime Algorithms: A Dynamic Programming Approach. Artificial Intelligence 126(1-2): 139-157.
36. Hintzman, D. L. 1994. Twenty-Five Years of Learning and Memory: Was the Cognitive Revolution a Mistake? In Attention and Performance, Volume XV, ed. C. Umlita and M. Moscovitch, chapter 16: 360-91. Cambridge, MA: The MIT Press.
37. Hobbs, J., and Gordon, A. 2005. Toward a Large-Scale Formal Theory of Common-sense Psychology for Metacognition. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and Oates. Menlo Park, CA: AAAI Press.
38. Holland, O., ed. 2003. Machine Consciousness. London: Academic Press.
39. Horvitz, E. 2001. Principles and Applications of Continual Computation. Artificial Intelligence 126(1-2): 159-96.
40. Hudlicka, E. 2005. Modeling Interactions between Metacognition and Emotion in a Cognitive Architecture. In Metacognition Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
41. Hume, D. 1740. A Treatise of Human Nature. Ed. D. F. Norton and M. J. Norton. Oxford: Oxford University Press, 2000.
42. Hutter, M. 2004. Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Berlin: Springer.
43. Josyula, D. 2005. A Unified Theory of Acting and Agency for a Universal Interfacing Agent. Ph.D. dissertation, Dept. of Computer Science, University of Maryland, College Park, MD.
44. Kennedy, C. 2003. Distributed Reflective Architectures for Anomaly Detection and Autonomous Recovery. Ph.D. dissertation, School of Computer Science, University Birmingham, Birmingham, UK.
45. Kim. J. 2005) Memory Based Meta-Level Reasoning for Interactive Knowledge Capture. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
46. Lundström, J.; Hamfelt A.; and Nilsson, 2005. Argumentation as a Metacognitive Skill of Passing Acceptance. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
47. Messina, E., and Meystel, A., eds. 2004. Proceedings of the 2004 Performance Metrics For Intelligent Systems Workshop. Gaithersburg, MD: National Institute of Standards and Technology.
48. Micchelli, C. A.; and Pontil, M. 2005. Kernels for Multitask Learning. In Proceedings of the 18th Conference on Neural Information Processing Systems. Cambridge, MA: The MIT Press.
49. Minsky, M. 1982. Why People Think Computers Can't. AI Magazine 3(4): 3-15.
50. Mitchell, M. 2005. Self-Awareness and Control in Decentralized Systems. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
51. Mitchell, T. 1991. The Need for Bias in Learning Generalizations. In Readings In Machine Learning, ed. T. Dietterich and J. Shavlik. San Francisco: Morgan Kaufmann Publishers.
52. Mitchell, T. 1997. Machine Learning. New York: McGraw-Hill.
53. Muldner, K., and Conati, C. 2005. Providing Adaptive Support for Meta-Cognitive Skills to Improve Learning. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
54. Murdock, J. W. 2001. Self-Improvement through Self-Understanding: Model-Based Reflection for Agent Adaptation. Ph.D. dissertation, Dept. of Computer Science, Georgia Institute of Technology, Atlanta, GA.
55. Oehlmann, R. 2003. Metacognitive and Computational Aspects of Chance Discovery. New Generation Computing 21(1): 3-12.
56. Pfahringer, B.; Bensusan, H.; and Giraud-Carrier, C. 2000. Metalearning by Land-marking Various Learning Algorithms. In Proceedings of the Seventeenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers.
57. Purang, K. 2001. Systems that Detect and Repair Their Own Mistakes. Ph.D. dissertation, Dept. of Computer Science, University of Maryland, College Park, MD.
58. Russell, S. 2002. Rationality and Intelligence. In Common Sense, Reasoning, and Rationality, ed. R. Elio, 337-59. Oxford: Oxford University Press.
59. Russell, S., and Wefald, E. 1991. Principles of Metareasoning. Artificial Intelligence 49(1-3): 361-95.
60. Sandholm, T. 2003. Principles and Practice of Constraint Programming. Lecture Notes In Computer Science, 2833: 950-55. Berlin: Springer.
61. Schaffer, C. 1994. A Conservation Law for Generalization Performance. In Proceedings of the Eleventh International Conference on Machine Learning, 259-65. San Francisco: Morgan Kaufmann Publishers.
62. Schmidhuber, J. 2005. Completely Self-Referential Optimal Reinforcement Learners. Paper presented at the International Conference on Artificial Neural Networks (IJC-NN), 31 July-4 August, Montreal, Quebec, Canada.
63. Schubert, L. 2005. Some Kr&R Requirements for Self-Awareness. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
64. Schut, M., and Wooldridge, M. 2001. Principles of Intention Reconsideration. In Proceedings of the Fifth International Conference on Autonomous Agents, 340-47. New York: Association for Computing Machinery.
65. Stolle, R.; Hogan, A.; and Bradley, E. 2005. Agenda Control for Heterogeneous Reasoners. Journal of Logic and Algebraic Programming 62(1): 41-69.
66. Sullivan, G. 2001. Aspect-Oriented Programming Using Reflection and Metaobject Protocols. Communications of the ACM 44(10): 95-7.
67. Swanson, R., and Gordon, A. 2005. Automated Commonsense Reasoning About Human Memory. In Metacognition in Computation: Papers from the 2005 AAAI Spring Symposium, Technical Report SS-05-04, ed. M. Anderson and T. Oates. Menlo Park, CA: AAAI Press.
68. Thrun, S. 1996. Is Learning the Nth Thing Any Easier Than Learning the First? Advances In Neural Information Processing Systems 8, 640-6. Cambridge, MA: The MIT Press.
69. Vilalta, R., and Drissi, Y. 2002. A Perspective View and Survey of Metalearning. Artificial Intelligence Review 18(2): 77-95.
70. Wallace, S. 2005. S-Assess: A Library for Self-Assessment. In Proceedings of the Fourth International Conference on Autonomous Agents and Multiagent Systems, 256-63. New York: Association for Computing Machinery.
71. Welch, I., and Stroud, R. J. 2002. Using Reflection as a Mechanism for Enforcing Security Policies on Compiled Code. Journal of Computer Security 10(4): 399-432.
72. Williams, B.; Ingham, M.; Chung, S.; Elliott, P.; and Hofbaur, M. 2004. Model-Based Programming of Fault-Aware Systems. AI Magazine 24(4): 61-75.
73. Wolpert, D. 1992. Stacked Generalization. Neural Networks 5(2): 241-59.
74. Wolpert, D. 2001. The Supervised Learning No Free Lunch Theorems. Paper presented at the Sixth On-Line World Conference on Soft Computing in Industrial Applications, Berlin, 10-24 September.
75. Wolpert, D., and Macready, W. 1995. No Free Lunch Theorems for Search. Technical Report SFI-TR-95-02-010. Santa Fe Institute, Santa Fe, NM.
76. Zachary, W., and Le Mentec, J.-C. 2000. Incorporating Metacognitive Capabilities in Synthetic Cognition. Paper presented at the Ninth Conference on Computer Generated Forces, Orlando, FL, May.
77. Zheng, J., and Horsch, M. 2005. A Decision Theoretic Meta-Reasoner for Constraint Optimization, Lecture Notes In Computer Science, 3501, 53-65. Berlin: Springer.