Skip to main content
Springer Nature Link
Log in

NeuroEvolution Based on Reusable and Hierarchical Modular Representation

  • Conference paper
Advances in Neuro-Information Processing (ICONIP 2008)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5506))

Included in the following conference series:

  • 2258 Accesses

Abstract

The framework of neuroevolution (NE) provides a way of finding appropriate structures as well as connection weights of artificial neural networks. However, the conventional NE approach of directly coding each connection weight by a gene is severely limited in its scalability and evolvability. In this study, we propose a novel indirect coding approach in which a phenotypical network develops from the genes encoding multiple subnetwork modules. Each gene encodes a subnetwork consisting of the input, hidden, and output nodes and connections between them. A connection can be a real weight or a pointer to another subnetwork. The structure of the network evolves by inserting new connection weights or subnetworks, merging two subnetworks as a higher-level subnetwork, or changing the existing connections. We investigated the evolutionary process of the network structure using the task of double pole balancing. We confirmed that the proposed method by the modular developmental rule can produce a wide variety of network architectures and that evolution can trim them down to the most appropriate ones required by the task.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Miikkulainen, R.: Evolving neural networks. In: Procs. of Genetic and Evolutionary Computation Conference (GECCO 2007), pp. 3415–3434. ACM, New York (2007)

    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. Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)

    Article  Google Scholar 

  4. Reisinger, J., Miikkulainen, R.: Acquiring evolvability through adaptive representations. In: Procs. of Genetic and Evolutionary Computation Conference (GECCO 2007), pp. 1045–1052. ACM, New York (2007)

    Google Scholar 

  5. Nolfi, S., Parisi, D.: “genotypes” for neural networks. In: The handbook of brain theory and neural networks table of contents, pp. 431–434 (1998)

    Google Scholar 

  6. Seys, C.W., Beer, R.D.: Effect of encoding on the evolvability of an embodied neural network. In: GECCO 2006 Workshop Procs., Workshop on Complexity through Development and Self-Organizing Representations (CODESOAR) (2006)

    Google Scholar 

  7. Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Procs. of the 9th International Conference on Parallel Problem Solving from Nature (PPSN IX). LNCS, vol. 9, pp. 671–680. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  8. Mattiussi, C., Floreano, D.: Analog genetic encoding for the evolution of circuits and networks. IEEE Transactions on Evolutionary Computation 11(5), 596–607 (2007)

    Article  Google Scholar 

  9. Gauci, J., Stanley, K.O.: A case study on the critical role of geometric regularity in machine learning. In: Procs. of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI 2008). AAAI Press, Menlo Park (2008) (to appear)

    Google Scholar 

  10. Kirschner, M., Gerhart, J.: Evolvability. Proceedings of the National Academy of Sciences (PNAS) 95(15), 8420–8427 (1998)

    Article  Google Scholar 

  11. Raff, R.A., Sly, B.J.: Modularity and dissociation in the evolution of gene expression territories in development. Evolution & Development 2(2), 102–113 (2000)

    Article  Google Scholar 

  12. Gruau, F.: Automatic definition of modular neural networks. Adaptive Behaviour 3(2), 151–183 (1995)

    Article  Google Scholar 

  13. Reisinger, J., Stanley, K.O., Miikkulainen, R.: Evolving reusable neural modules. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 69–81. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  14. Walker, J.A., Miller, J.F.: Automatic acquisition, evolution and re-use of modules in cartesian genetic programming. IEEE Transactions on Evolutionary Computation 12(4) (August 2008)

    Google Scholar 

  15. Schaffer, J.D., Whitley, D., Eshelman, L.J.: Combinations of genetic algorithms and neural networks: a survey of the state of the art. In: International workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN 1992), pp. 1–37 (1992)

    Google Scholar 

  16. Radcliffe, N.J.: Forma analysis and random respectful recombination. In: Procs. of the Fourth International Conference on Genetic Algorithms, pp. 222–229. Morgan Kaufmann Publishers, San Francisco (1991)

    Google Scholar 

  17. Kassahun, Y.: Towards a Unified Approach to Learning and Adaptation. PhD thesis, Inst. f. Informatik u. Prakt. Math. der Christian-Albrechts-Universität zu Kiel (2006)

    Google Scholar 

  18. Siebel, N.T., Sommer, G.: Evolutionary reinforcement learning of artificial neural networks. International Journal of Hybrid Intelligent Systems 4(3), 171–183 (2007)

    Article  MATH  Google Scholar 

  19. Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation 9(2), 159–195 (2001)

    Article  Google Scholar 

  20. Igel, C.: Neuroevolution for reinforcement learning using evolution strategies. In: Procs. of Congress on Evolutionary Computation (CEC 2003), vol. 4, pp. 2588–2595. IEEE Press, Los Alamitos (2003)

    Google Scholar 

  21. Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: Genetic Programming 1996: Procs. of the First Annual Conference, pp. 81–89. MIT Press, Cambridge (1996)

    Google Scholar 

  22. Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated neural evolution through cooperatively coevolved synapses. The Journal of Machine Learning Research 9, 937–965 (2008)

    MathSciNet  MATH  Google Scholar 

  23. Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Evolutionary development of hierarchical learning structures. IEEE Transactions on Evolutionary Computations 11(2), 249–264 (2007)

    Article  Google Scholar 

  24. Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Darwinian embodied evolution of the learning ability for survival. Adaptive Behavior (to appear)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Okinawa Institute of Science and Technology, Okinawa, Japan

    Takumi Kamioka, Eiji Uchibe & Kenji Doya

  2. Nara Institute of Science and Technology, Nara, Japan

    Takumi Kamioka & Kenji Doya

  3. ATR Computational Neuroscience Laboratories, Kyoto, Japan

    Kenji Doya

Authors
  1. Takumi Kamioka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Eiji Uchibe
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kenji Doya
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Kyushu Institute of Technology, Network Design and Research Center, 680-4 Fukuoka, 820-8502, Kawazu, Iizuka, Japan

    Mario Köppen

  2. Knowledge Engineering and Discovery Research Institute (KEDRI), School of Computing and Mathematical Sciences, Auckland University of Technology, 350 Queen Street, 10110, Auckland, New Zealand

    Nikola Kasabov

  3. Department of Electrical and Computer Engineering, Robotics Laboratory, Auckland University of Technology, 38 Princes Street, 1142, Auckland, New Zealand

    George Coghill

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kamioka, T., Uchibe, E., Doya, K. (2009). NeuroEvolution Based on Reusable and Hierarchical Modular Representation. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5506. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02490-0_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-02490-0_3

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-02489-4

  • Online ISBN: 978-3-642-02490-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics