Advertisement

Accuracy in Symbolic Regression

  • Michael F. Korns
Chapter
Part of the Genetic and Evolutionary Computation book series (GEVO)

Abstract

This chapter asserts that, in current state-of-the-art symbolic regression engines, accuracy is poor. That is to say that state-of-the-art symbolic regression engines return a champion with good fitness; however, obtaining a champion with the correct formula is not forthcoming even in cases of only one basis function with minimally complex grammar depth. Ideally, users expect that for test problems created with no noise, using only functions in the specified grammar, with only one basis function and some minimal grammar depth, that state-of-the-art symbolic regression systems should return the exact formula (or at least an isomorph) used to create the test data. Unfortunately, this expectation cannot currently be achieved using published state-of-the-art symbolic regression techniques. Several classes of test formulas, which prove intractable, are examined and an understanding of why they are intractable is developed. Techniques in Abstract Expression Grammars are employed to render these problems tractable, including manipulation of the epigenome during the evolutionary process, together with breeding of multiple targeted epigenomes in separate population islands. Aselected set of currently intractable problems are shown to be solvable, using these techniques, and a proposal is put forward for a discipline-wide program of improving accuracy in state-of-the-art symbolic regression systems.

Keywords

Abstract Expression Grammars Differential Evolution Grammar Template Genetic Programming Genetic Algorithms Particle Swarm Symbolic Regression. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Castillo, Flor, Kordon, Arthur, and Villa, Carlos (2010). Genetic programming transforms in linear regression situations. In Riolo, Rick,McConaghy, Trent, and Vladislavleva, Ekaterina, editors, Genetic Programming Theory and Practice VIII, volume 8 of Genetic and Evolutionary Computation, chapter 11, pages 175–194. Springer, Ann Arbor, USA.Google Scholar
  2. Eberhart, Russell, Shi, Yuhui, and Kennedy, James (2001). Hidden Order: How Adaptation Builds Complexity. Springer, New York.Google Scholar
  3. Hornby, Gregory S. (2006). ALPS: the age-layered population structure for reducing the problem of premature convergence. In Keijzer, Maarten et al., editors, GECCO 2006: Proceedings of the 8th annual conference on Genetic and evolutionary computation, volume 1, pages 815–822, Seattle, Washington, USA. ACM Press.Google Scholar
  4. Korns, Michael F. (2009). Symbolic regression of conditional target expressions. In Riolo, Rick L., O’Reilly, Una-May, and McConaghy, Trent, editors, Genetic Programming Theory and Practice VII, Genetic and Evolutionary Computation, chapter 13, pages 211–228. Springer, Ann Arbor.Google Scholar
  5. Korns, Michael F. (2010). Abstract expression grammar symbolic regression. In Riolo, Rick, McConaghy, Trent, and Vladislavleva, Ekaterina, editors, Genetic Programming Theory and Practice VIII, volume 8 of Genetic and Evolutionary Computation, chapter 7, pages 109–128. Springer, Ann Arbor, USA.Google Scholar
  6. Koza, John R. (1992). Genetic Programming: On the Programming of Computers Google Scholar
  7. by Means of Natural Selection. MIT Press, Cambridge, MA, USA.Google Scholar
  8. Man, KimFung, Tang, KitSang, and Kwong, Sam (1999). Genetic Algorithms. Springer, New York.Google Scholar
  9. McConaghy, Trent, Palmers, Pieter, Gao, Peng, Steyaert, Michiel, and Gielen, Georges (2009). Variation-Aware Analog Structural Synthesis - A Computational Intelligence Approach. Analog Circuits and Signal Processing. Springer, Netherlands.Google Scholar
  10. McKay, Robert I., Hoai, Nguyen Xuan,Whigham, Peter Alexander, Shan, Yin, and O’Neill, Michael (2010). Grammar-based genetic programming: a survey. GeneticProgramming andEvolvableMachines, 11(3/4):365–396. TenthGoogle Scholar
  11. Anniversary Issue: Progress in Genetic Programming and Evolvable Machines. O´Neill, Michael and Ryan, Conor (2003). Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language. Kluwer Academic Publishers, Dordrecht Netherlands.Google Scholar
  12. Price, Kenneth, Storn, Rainer, and Lampinen, Jouni (2005). Differential Evolution: Google Scholar
  13. A Practical Approach to Global Optimization. Springer, New York.Google Scholar
  14. Ryan, Conor,Keijzer,Maarten, andCattolico,Mike (2005). Favourable Biasing of Function Sets using Run Transferable Libraries in Genetic Programming Theory and Practice II. Springer, New York.Google Scholar
  15. Schmidt, Michael and Lipson, Hod (2010). Age-fitness pareto optimization. In Riolo, Rick, McConaghy, Trent, and Vladislavleva, Ekaterina, editors, Genetic Programming Theory and Practice VIII, volume 8 of Genetic and Evolutionary Computation, chapter 8, pages 129–146. Springer, Ann Arbor, USA.Google Scholar
  16. Smits, Guido F., Vladislavleva, Ekaterina, and Kotanchek, Mark E. (2010). Scalable symbolic regression by continuous evolution with very small populations. In Riolo, Rick, McConaghy, Trent, and Vladislavleva, Ekaterina, editors, Genetic Programming Theory and Practice VIII, volume 8 of Genetic and Evolutionary Computation, chapter 9, pages 147–160. Springer, Ann Arbor, USA.Google Scholar
  17. Spector, Lee (2010). Towards practical autoconstructive evolution: Selfevolution of problem-solving genetic programming systems. In Riolo, Rick, McConaghy, Trent, and Vladislavleva, Ekaterina, editors, Genetic Programming Theory and Practice VIII, volume 8 of Genetic and Evolutionary Computation, chapter 2, pages 17–33. Springer, Ann Arbor, USA.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Michael F. Korns
    • 1
  1. 1.Korns AssociatesMakatiPhilippines

Personalised recommendations