Skip to main content
SpringerLink
Log in

Extending Genetic Programming to Evolve Perceptron-Like Learning Programs

  • Conference paper
Artifical Intelligence and Soft Computing (ICAISC 2010)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 6114))

Included in the following conference series:

  • 1945 Accesses

Abstract

We extend genetic programming (GP) with a local memory and vectorization to evolve simple, perceptron-like programs capable of learning by error correction. The local memory allows for a scalar value or vector to be stored and manipulated within a local scope of GP tree. Vectorization consists in grouping input variables and processing them as vectors. We demonstrate these extensions, along with an island model, allow to evolve general perceptron-like programs, i.e. working for any number of inputs. This is unlike in standard GP, where inputs are represented explicitly as scalars, so that scaling up the problem would require to evolve a new solution. Moreover, we find vectorization allows to represent programs more compactly and facilitates the evolutionary search.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Christensen, S., Oppacher, F.: An Analysis of Koza’s Computational Effort Statistic for Genetic Programming. In: Foster, J.A., Lutton, E., Miller, J., Ryan, C., Tettamanzi, A.G.B. (eds.) EuroGP 2002. LNCS, vol. 2278, pp. 182–191. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  2. Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: From Architectures to Learning. Evolutionary Intelligence 1(1), 47–62 (2008)

    Article  Google Scholar 

  3. Koza, J.R.: Genetic Programming III: Darwinian Invention and Problem Solving. Morgan Kaufmann Pub., San Francisco (1999)

    MATH  Google Scholar 

  4. Koza, J.R., Keane, M.A., Streeter, M.J.: What’s AI Done for Me Lately? Genetic Programming’s Human-Competitive Results. IEEE Intell. Syst., 25–31 (2003)

    Google Scholar 

  5. Miikkulainen, R.: Evolving Neural Networks. In: Proc. of the 2007 GECCO Conf. Comp. on Genetic and Evol. Comput., pp. 3415–3434. ACM, New York (2007)

    Chapter  Google Scholar 

  6. Montana, D.J.: Strongly Typed Genetic Programming. Evolutionary Computation 3(2), 199–230 (1995)

    Article  Google Scholar 

  7. Poli, R., Langdon, W.B., McPhee, N.F.: A Field Guide to Genetic Programming. Lulu Press (2008)

    Google Scholar 

  8. Teller, A.: Turing Completeness in the Language of Genetic Programming with Indexed Memory. In: Proc. of the 1994 IEEE World Congr. on Comput. Intell., vol. 1, pp. 136–141 (1994)

    Google Scholar 

  9. Tomassini, M.: Spatially Structured Evolutionary Algorithms. Springer, Heidelberg (2005)

    MATH  Google Scholar 

  10. Widrow, B., Lehr, M.A.: 30 Years of Adaptive Neural Networks: Perceptron, Madaline and Backpropagation. Proc. IEEE 78(9), 1415–1442 (1990)

    Article  Google Scholar 

  11. Woodward, J.R., Bai, R.: Why Evolution Is Not a Good Paradigm for Program Induction: A Critique of Genetic Programming. In: Proc. of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, pp. 593–600 (2009)

    Google Scholar 

  12. Yao, X.: Evolving Artificial Neural Networks. Proc. IEEE 87(9), 1423–1447 (1999)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, ul. Żołnierska 49, 71-210, Szczecin, Poland

    Marcin Suchorzewski

Authors
  1. Marcin Suchorzewski
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Artificial Intelligence, Academy of Humanities and Economics, Poland

    Leszek Rutkowski

  2. Academy of Humanities and Economics in Łódź, ul. Rewolucji 1905 nr 64, Łódź, Poland

    Rafał Scherer

  3. Institute of Automatics, AGH University of Science and Technology, Al. Mickiewicza 30, PL-30-059, Kraków, Poland

    Ryszard Tadeusiewicz

  4. Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley Initiative in Soft Computing (BISC), 94720-1776, CA

    Lotfi A. Zadeh

  5. Computational Intelligence Laboratory Department of Electrical and Computer Engineering, University of Louisville, 40292, Louisville, KY

    Jacek M. Zurada

Rights and permissions

Reprints and permissions

Copyright information

© 2010 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Suchorzewski, M. (2010). Extending Genetic Programming to Evolve Perceptron-Like Learning Programs. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artifical Intelligence and Soft Computing. ICAISC 2010. Lecture Notes in Computer Science(), vol 6114. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13232-2_27

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-13232-2_27

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-13231-5

  • Online ISBN: 978-3-642-13232-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation