Advertisement

NEAT in HyperNEAT Substituted with Genetic Programming

  • Zdeněk Buk
  • Jan Koutník
  • Miroslav Šnorek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5495)

Abstract

In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.

Keywords

Neural Network Genetic Programming Mobile Agent Recurrent Neural Network Neural Controller 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge (1992)zbMATHGoogle Scholar
  2. 2.
    D’Ambrosio, D.B., Stanley, K.O.: A novel generative encoding for exploiting neural network sensor and output geometry. In: GECCO 2007: Proceedings of the 9th annual conference on Genetic and evolutionary computation, pp. 974–981. ACM, New York (2007)Google Scholar
  3. 3.
    Gauci, J., Stanley, K.: Generating large-scale neural networks through discovering geometric regularities. In: GECCO 2007: Proceedings of the 9th annual conference on Genetic and evolutionary computation, pp. 997–1004. ACM, New York (2007)Google Scholar
  4. 4.
    Drchal, J., Koutník, J., Šnorek, M.: Hyperneat controlled robots learn to drive on roads in simulated environment. In: Submitted to IEEE Congress on Evolutionary Computation (CEC 2009) (2009)Google Scholar
  5. 5.
    Mattiussi, C.: Evolutionary synthesis of analog networks. Ph.D thesis, EPFL, Lausanne (2005)Google Scholar
  6. 6.
    Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with Analog Genetic Encoding. In: Parallel Problem Solving from Nature - PPSN iX, vol. 9, pp. 671–680. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Dürr, P., Mattiussi, C., Soltoggio, A., Floreano, D.: Evolvability of Neuromodulated Learning for Robots. In: The 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, pp. 41–46. IEEE Computer Society, Los Alamitos (2008)CrossRefGoogle Scholar
  8. 8.
    Buk, Z., Šnorek, M.: Hybrid evolution of heterogeneous neural networks. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 426–434. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Angeline, P.J., Saunders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 5, 54–65 (1993)CrossRefGoogle Scholar
  10. 10.
    Schmidhuber, J., Wierstra, D., Gagliolo, M., Gomez, F.: Training recurrent networks by evolino. Neural computation 19(3), 757–779 (2007)CrossRefzbMATHGoogle Scholar
  11. 11.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10, 99–127 (2002)CrossRefGoogle Scholar
  12. 12.
    D’Ambrosio, D.B., Stanley, K.O.: Generative encoding for multiagent learning. In: GECCO 2008: Proceedings of the 10th annual conference on Genetic and evolutionary computation, pp. 819–826. ACM, New York (2008)Google Scholar
  13. 13.
    Waibel, M.: Evolution of Cooperation in Artificial Ants. Ph.D thesis, EPFL (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Zdeněk Buk
    • 1
  • Jan Koutník
    • 1
  • Miroslav Šnorek
    • 1
  1. 1.Computational Intelligence Group Department of Computer Science and Engineering Faculty of Electrical EngineeringCzech Technical University in PragueCzechia

Personalised recommendations