Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Speedup Learning

  • Alan Fern
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_772

Definition

Speedup learning is a branch of machine learning that studies learning mechanisms for speeding up problem solvers based on problem-solving experience. The input to a speedup learner typically consists of observations of prior problem-solving experience, which may include traces of the problem solver’s operations and/or solutions to solve the problems. The output is knowledge that the problem solver can exploit to find solutions more quickly than before learning without seriously effecting the solution quality. The most distinctive feature of speedup learning, compared with most branches of machine learning, is that the learned knowledge does not provide the problem solver with the ability to solve new problem instances. Rather, the learned knowledge is intended solely to facilitate faster solution times compared to the solver without the knowledge.

Motivation and Background

Much of the work in computer science and especially artificial intelligence aims at developing...

This is a preview of subscription content, log in to check access.

Recommended Reading

  1. Beame, P., Kautz, H., & Sabharwal, A. (2004). Towards understanding and harnessing the potential of clause learning. Journal of Artificial Intelligence Research22, 319–351.MathSciNetMATHGoogle Scholar
  2. Boyan, J. A., & Moore, A. W. (1998). Learning evaluation functions for global optimization and boolean satisfiability. In National conference on artificial intelligence (pp. 3–10). Mlenio Park, CA: AAAI Press.Google Scholar
  3. Fikes, R., Hart, P., & Nilsson, N. (1972). Learning and executing generalized robot plans. Artificial Intelligence3(1–3), 251–288.CrossRefGoogle Scholar
  4. Huang, Y.-C., Selman, B., & Kautz, H. (2000). Learning declarative control rules for constraint-based planning. In International conference on machine learning (pp. 415–422). San Francisco: Morgan Kaufmann.Google Scholar
  5. Kambhampati, S. (1998). On the relations between intelligent backtracking and failure-driven explanation-based learning in constraint satisfaction and planning. Artificial Intelligence, 105(1-2), 161–208.MATHCrossRefGoogle Scholar
  6. Khardon, R. (1999). Learning action strategies for planning domains. Artificial Intelligence, 113(1-2), 125–148.MATHCrossRefGoogle Scholar
  7. Kumar, V., & Lin, Y. (1988). A data-dependency based intelligent backtracking scheme for prolog. The Journal of Logic Programming5(2), 165–181.MathSciNetMATHCrossRefGoogle Scholar
  8. Minton, S. (1988). Quantitative results concerning the utility of explanation-based learning. In National conference on artificial intelligence (pp. 564–569). St. Paul, MN: Morgan Kaufmann.Google Scholar
  9. Minton, S. (Ed.) (1993). Machine learning methods for planning. San Francisco: Morgan Kaufmann.Google Scholar
  10. Minton, S., Carbonell, J., Knoblock, C. A., Kuokka, D. R., Etzioni, O., & Gil, Y.  (1989). Explanation-based learning: A problem solving perspective. Artificial Intelligence40, 63–118.CrossRefGoogle Scholar
  11. Samuel, A. (1959). Some studies in machine learning using the game of checkers. IBM Journal of Research and Development3(3), 211–229.MathSciNetCrossRefGoogle Scholar
  12. Sarkar, S., Chakrabarti, P., & Ghose, S. (1998). Learning whiles solving problems in best first search. IEEE Transactions on Systems, Man, and Cybernetics–Part A: Systems and Humans28(4), 553–541.Google Scholar
  13. Schiex, T., & Verfaillie, G. (1994). Nogood recording for static and dynamic constraint satisfaction problems. International Journal on Artificial Intelligence Tools3(2), 187–207.CrossRefGoogle Scholar
  14. Tadepalli, P., & Natarajan, B. (1996). A formal framework for speedup learning from problems and solutions. Journal of Artificial Intelligence Research4, 445–475.MathSciNetMATHGoogle Scholar
  15. Zimmerman, T., & Kambhampati, S. (2003). Learning-assisted automated planning: Looking back, taking stock, going forward. AI Magazine24(2), 73–96.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Alan Fern

There are no affiliations available