Jump to ContentJump to Main Navigation
Show Summary Details
More options …

International Journal of Applied Mathematics and Computer Science

Journal of University of Zielona Gora and Lubuskie Scientific Society

4 Issues per year


IMPACT FACTOR 2016: 1.420
5-year IMPACT FACTOR: 1.597

CiteScore 2016: 1.81

SCImago Journal Rank (SJR) 2016: 0.524
Source Normalized Impact per Paper (SNIP) 2016: 1.440

Mathematical Citation Quotient (MCQ) 2016: 0.08

Open Access
Online
ISSN
2083-8492
See all formats and pricing
More options …
Volume 24, Issue 1 (Mar 2014)

Issues

Cross-task code reuse in genetic programming applied to visual learning

Wojciech Jaśkowski
  • Corresponding author
  • Institute of Computing Science Pozna´n University of Technology, ul. Piotrowo 2, 60-965 Poznań, Poland
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Krzysztof Krawiec
  • Corresponding author
  • Institute of Computing Science Pozna´n University of Technology, ul. Piotrowo 2, 60-965 Poznań, Poland
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Bartosz Wieloch
  • Corresponding author
  • Institute of Computing Science Pozna´n University of Technology, ul. Piotrowo 2, 60-965 Poznań, Poland
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
Published Online: 2014-03-25 | DOI: https://doi.org/10.2478/amcs-2014-0014

Abstract

We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a visual learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit visual similarity.

Keywords: genetic programming; code reuse; knowledge sharing; visual learning; multi-task learning; optical character recognition.

References

  • Bhanu, B., Lin, Y. and Krawiec, K. (2005). Evolutionary Synthesisof Pattern Recognition Systems, Springer-Verlag, New York, NY.Google Scholar

  • Caruana, R. (1997). Multitask learning, Machine Learning28(1): 41-75.Google Scholar

  • Chang, Y.F., Lee, J.C., Mohd Rijal, O. and Syed Abu Bakar, S.A.R. (2010). Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model, International Journal of AppliedMathematics and Computer Science 20(4): 727-738, DOI: 10.2478/v10006-010-0055-x.CrossrefGoogle Scholar

  • Ciresan, D.C., Meier, U. and Schmidhuber, J. (2012). Multi-column deep neural networks for image classification, Proceedings of the 2012 IEEE Conferenceon Computer Vision and Pattern Recognition(CVPR), Providence, RI, USA, pp. 3642-3649.Google Scholar

  • Fabijańska, A. (2012). A survey of subpixel edge detection methods for images of heat-emitting metal specimens, International Journal of Applied Mathematicsand Computer Science 22(3): 695-710, DOI: 10.2478/v10006-012-0052-3.CrossrefGoogle Scholar

  • Galvan Lopez, E., Poli, R. and Coello Coello, C.A. (2004). Reusing code in genetic programming, in M. Keijzer, U.-M. O’Reilly, S.M. Lucas, E. Costa and T. Soule (Eds.), Genetic Programming-7th European Conference,EuroGP 2004, Proceedings, Lecture Notes in Computer Science, Vol. 3003, Springer-Verlag, Berlin/Heidelberg, pp. 359-368.Google Scholar

  • Ghosn, J. and Bengio, Y. (2003). Bias learning, knowledge sharing, IEEE Transactions on Neural Networks14(4): 748-765.CrossrefWeb of ScienceGoogle Scholar

  • Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P. and Witten, I.H. (2009). The Weka data mining software: An update, SIGKDD Explorations 11(1): 10-18.Google Scholar

  • Haynes, T. (1997). On-line adaptation of search via knowledge reuse, in J.R. Koza, K. Deb, M. Dorigo, D.B. Fogel, M. Garzon, H. Iba and R.L. Riolo (Eds.), GeneticProgramming 1997: Proceedings of the Second AnnualConference, Morgan Kaufmann, San Francisco, CA, pp. 156-161.Google Scholar

  • Holland, J. (1975). Adaptation in Natural and Artificial Systems, Vol. 1, University of Michigan Press, Ann Arbor, MI.Google Scholar

  • Hornby, G.S. and Pollack, J.B. (2002). Creating high-level components with a generative representation for body-brain evolution, Artificial Life 8(3): 223-246.Google Scholar

  • Howard, D. (2003). Modularization by multi-run frequency driven subtree encapsulation, in R.L. Riolo and B. Worzel (Eds.), Genetic Programming Theory and Practice, Kluwer, New York, NY, Chapter 10, pp. 155-172.Google Scholar

  • Howard, D., Roberts, S.C. and Ryan, C. (2006). Pragmatic genetic programming strategy for the problem of vehicle detection in airborne reconnaissance, Pattern RecognitionLetters 27(11): 1275-1288.Google Scholar

  • Hsu, W.H., Harmon, S.J., Rodriguez, E. and Zhong, C. (2004). Empirical comparison of incremental reuse strategies in genetic programming for keep-away soccer, in M. Keijzer (Ed.), Late Breaking Papers at the 2004 Genetic andEvolutionary Computation Conference, Association for Computing Machinery, Seattle, WA.Google Scholar

  • Jaśkowski, W., Krawiec, K. and Wieloch, B. (2007a). Genetic programming for cross-task knowledge sharing, in D. Thierens (Ed.), Genetic and Evolutionary ComputationConference GECCO, Association for Computing Machinery, London, pp. 1620-1627.Google Scholar

  • Jaśkowski, W., Krawiec, K. and Wieloch, B. (2007b). Knowledge reuse in genetic programming applied to visual learning, in D. Thierens (Ed.), Genetic and EvolutionaryComputation Conference GECCO, Association for Computing Machinery, London, pp. 1790-1797.Google Scholar

  • Jaśkowski, W., Krawiec, K. and Wieloch, B. (2007c). Learning and recognition of hand-drawn shapes using generative genetic programming, in M. Giacobini (Ed.), EvoWorkshops2007, Lecture Notes in Computer Science, Vol. 4448, Springer-Verlag, Berlin/Heidelberg, pp. 281-290.Google Scholar

  • Koza, J. (1992). Genetic Programming, MIT Press, Cambridge, MA.Google Scholar

  • Koza, J.R. (1994). Genetic Programming II: Automatic Discoveryof Reusable Programs, MIT Press, Cambridge, MA.Google Scholar

  • Koza, J.R., Bennett III, F.H., Andre, D. and Keane, M.A. (1996). Reuse, parameterized reuse, and hierarchical reuse of substructures in evolving electrical circuits using genetic programming, in T. Higuchi (Ed.), Proceedings of InternationalConference on Evolvable Systems: From Biology toHardware (ICES-96), Lecture Notes in Computer Science, Vol. 1259, Springer-Verlag, Berlin.Google Scholar

  • Krawiec, K. (2006). Learning high-level visual concepts using attributed primitives and genetic programming, in F. Rothlauf (Ed.), EvoWorkshops 2006, Lecture Notes in Computer Science, Vol. 3907, Springer-Verlag, Berlin/Heidelberg, pp. 515-519.Google Scholar

  • Krawiec, K. (2007). Generative learning of visual concepts using multiobjective genetic programming, Pattern RecognitionLetters 28(16): 2385-2400.Google Scholar

  • Krawiec, K. and Bhanu, B. (2005). Visual learning by coevolutionary feature synthesis, IEEE Transactions onSystem, Man, and Cybernetics, Part B 35(3): 409-425.Google Scholar

  • Kurashige, K., Fukuda, T. and Hoshino, H. (2003). Reusing primitive and acquired motion knowledge for gait generation of a six-legged robot using genetic programming, Journal of Intelligent and Robotic Systems38(1): 121-134. Google Scholar

  • Langdon, W.B. and Poli, R. (2002). Foundations of Genetic Programming, Springer-Verlag, New York, NY.Google Scholar

  • Li, B., Li, X., Mabu, S. and Hirasawa, K. (2012). Towards automatic discovery and reuse of subroutines in variable size genetic network programming, in X. Li (Ed.), Proceedingsof the 2012 IEEE Congress on Evolutionary Computation,Brisbane, Australia, pp. 485-492.Google Scholar

  • Louis, S. and McDonnell, J. (2004). Learning with case-injected genetic algorithms, IEEE Transactions on EvolutionaryComputation 8(4): 316-328.Google Scholar

  • Luke, S. (2002). ECJ evolutionary computation system, http://cs.gmu.edu/eclab/projects/ecj/.Google Scholar

  • Mitchell, T.M. (2006). The discipline of machine learning, Technical Report CMU-ML-06-108, Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA.Google Scholar

  • Montana, D.J. (1993). Strongly typed genetic programming, BBN Technical Report #7866, Bolt Beranek and Newman, Inc., Cambridge, MA.Google Scholar

  • Moya, M.R., Koch, M.W. and Hostetler, L.D. (1993). One-class classifier networks for target recognition applications, World Congress on Neural Networks, Portland, OR, USA, pp. 797-801.Google Scholar

  • O’Sullivan, J. and Thrun, S. (1995). A Robot That ImprovesIts Ability to Learn, Carnegie Mellon University, School of Computer Science, Pittsburgh, PA.Google Scholar

  • Poli, R., Langdon, W.B. and McPhee I.N.F. (2008). A field guide to genetic programming, http://www.gp-field-guide.org.uk/.Google Scholar

  • Perez, C.B. and Olague, G. (2013). Genetic programming as strategy for learning image descriptor operators, IntelligentData Analysis 17(4): 561-583.Web of ScienceGoogle Scholar

  • Pratt, L.Y., Mostow, J. and Kamm, C.A. (1991). Direct transfer of learned information among neural networks, Proceedingsof the 9th National Conference on Artificial Intelligence(AAAI-91), Anaheim, CA, USA, pp. 584-589.Google Scholar

  • Rizki, M.M., Zmuda, M.A. and Tamburino, L.A. (2002). Evolving pattern recognition systems, IEEE Transactionson Evolutionary Computation 6(6): 594-609.Google Scholar

  • Roberts, S.C., Howard, D. and Koza, J.R. (2001). Evolving modules in genetic programming by subtree encapsulation, in J.F. Miller (Ed.), Genetic Programming, Proceedings ofEuroGP’2001, Lecture Notes in Computer Science, Vol. 2038, Springer-Verlag, Berlin, pp. 160-175.Google Scholar

  • Rosca, J.P. and Ballard, D.H. (1996). Discovery of subroutines in genetic programming, in P.J.Angeline and K.E.Kinnear, Jr. (Eds.), Advances in Genetic Programming 2,MIT Press, Cambridge, MA, Chapter 9, pp. 177-202.Google Scholar

  • Seront, G. (1995). External concepts reuse in genetic programming, in E.V. Siegel and J.R. Koza (Eds.), WorkingNotes for the AAAI Symposium on Genetic Programming, AAAI/MIT, Cambridge, MA, pp. 94-98.Google Scholar

  • Tackett,W.A. (1993). Genetic generation of “dendritic” trees for image classification, Proceedings of theWorld Congress onNeural Networks, Portland, OR, USA, pp. IV 646-649. Google Scholar

  • Teller, A. and Veloso, M. (1997). PADO: A new learning architecture for object recognition, in K. Ikeuchi and M. Veloso (Eds.), Symbolic Visual Learning, Oxford Press, New York, NY, pp. 77-112.Google Scholar

  • Trujillo, L. and Olague, G. (2006). Synthesis of interest point detectors through genetic programming, in M. Cattolico (Ed.), Genetic and Evolutionary Computation ConferenceGECCO, Association for Computing Machinery, Seattle, WA, pp. 887-894.Google Scholar

  • Vilalta, R. and Drissi, Y. (2002). A perspective view and survey of meta-learning, Artificial Intelligence Review18(2): 77-95.CrossrefGoogle Scholar

  • Whitley, D., Rana, S. and Heckendorn, R. (1999). The island model genetic algorithm: On separability, population size and convergence, Journal of Computing and InformationTechnology 7(1): 33-47. Google Scholar

About the article

Wojciech Jaśkowski

Wojciech Ja´skowski received his B.Eng., M.Sc. and Ph.D. degrees in computing science from the Pozna´n University of Technology, Poland, in 2004, 2006 and 2011, respectively. Currently he is an assistant professor at the Laboratory of Intelligent Decision Support Systems, Institute of Computing Science, Pozna´n University of Technology. He is an author of more than 30 publications in computational intelligence, evolutionary computations in particular. His main research addresses co-evolution, co-optimization, genetic programming, temporal difference learning as well as learning strategies in interactive domains and games.

Krzysztof Krawiec

Krzysztof Krawiec received his Ph.D. and habilitation degrees from the Pozna´n University of Technology, in 2000 and 2005, respectively. He is an associate professor at the same university and works mainly on topics related to evolutionary computation, genetic programming, and pattern recognition. His recent work includes evolutionary computation for machine learning, primarily for learning game strategies and for synthesis of pattern recognition systems; semantics in genetic programming, particularly in operator design and problem decomposition; coevolutionary algorithms, mainly the role of interactions and coordinate systems for test-based problems; and the modeling of complex phenomena using genetic programming (e.g., climate modeling). Doctor Krawiec is the author of Evolutionary Synthesis of Pattern Recognition Systems (Springer, 2005), and the president of the Polish Chapter of the IEEE Computational Intelligence Society for the term 2013–2014.

Bartosz Wieloch

Bartosz Wieloch received his B.Eng., M.Sc. and Ph.D. degrees in computing science from the Pozna´n University of Technology, Poland, in 2004, 2006 and 2013, respectively. Currently, he is an assistant professor at the same university, in the Laboratory of Intelligent Decision Support Systems, Institute of Computing Science. His main research interests include semantics in genetic programming, pattern recognition and image analysis.


Published Online: 2014-03-25

Published in Print: 2014-03-01


Citation Information: International Journal of Applied Mathematics and Computer Science, ISSN (Print) 1641-876X, DOI: https://doi.org/10.2478/amcs-2014-0014.

Export Citation

This content is open access.

Comments (0)

Please log in or register to comment.
Log in