Advertisement

Neuroevolution with Analog Genetic Encoding

  • Peter Dürr
  • Claudio Mattiussi
  • Dario Floreano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4193)

Abstract

The evolution of artificial neural networks (ANNs) is often used to tackle difficult control problems. There are different approaches to the encoding of neural networks in artificial genomes. Analog Genetic Encoding (AGE) is a new implicit method derived from the observation of biological genetic regulatory networks. This paper shows how AGE can be used to simultaneously evolve the topology and the weights of ANNs for complex control systems. AGE is applied to a standard benchmark problem and we show that its performance is equivalent or superior to some of the most powerful algorithms for neuroevolution in the literature.

Keywords

Neural Network Hide Neuron Synaptic Weight Terminal Sequence Double Pole 
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.
    Maniezzo, V.: Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks 5(1), 39–53 (1994)CrossRefGoogle Scholar
  2. 2.
    Pujol, J., Poli, R.: Evolving the topology and the weights of neural networks using a dual representation. Applied Intelligence 8(1), 73–84 (1998)CrossRefGoogle Scholar
  3. 3.
    Kobayashi, K., Ohbayashi, M.: A new indirect encoding method with variable length gene code to optimize neural network structures. In: Proceedings of the International Joint Conference on Neural Networks, vol. 6, pp. 4409–4412 (1999)Google Scholar
  4. 4.
    Stanley, K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  5. 5.
    Cangelosi, A., Parisi, D., Nolfi, S.: Cell division and migration in a genotype for neural networks. Network: Computation in Neural Systems 5(4), 497–515 (1994)MATHCrossRefGoogle Scholar
  6. 6.
    Gruau, F.: Automatic definition of modular neural networks. Adaptive Behaviour 3(2), 151–183 (1995)CrossRefGoogle Scholar
  7. 7.
    Nolfi, S., Parisi, D.: Genotypes for neural networks. In: Arbib, M. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 431–434. MIT Press, Cambridge (1995)Google Scholar
  8. 8.
    Eggenberger, P.: Creation of neural networks based on developmental and evolutionary principles. In: Proceedings of the International Conference on Artificial Neural Networks, Lausanne, Switzerland (1997)Google Scholar
  9. 9.
    Astor, J., Adami, C.: A developmental model for the evolution of artificial neural networks. Artificial Life 6(3), 189–218 (2000)CrossRefGoogle Scholar
  10. 10.
    Mattiussi, C.: Evolutionary synthesis of analog networks. Ph.D. dissertation n.3199, EPFL, Lausanne (2005)Google Scholar
  11. 11.
    Bongard, J.: Evolving modular genetic regulatory networks. In: Proceedings of the IEEE 2002 Congress on Evolutionary Computation, CEC 2002, pp. 1872–1877. IEEE Press, Piscataway (2002)CrossRefGoogle Scholar
  12. 12.
    Mattiussi, C., Floreano, D.: Evolution of analog networks using local string alignment on highly reorganizable genomes. In: Proceedings of the 2004 NASA/DoD Conference on Evolvable Hardware, pp. 30–37 (2004)Google Scholar
  13. 13.
    Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: Genetic Programming 1996: Proceedings of the First Annual Conference, pp. 81–89 (1996)Google Scholar
  14. 14.
    Gomez, F.J., Miikkulainen, R.: Solving non-markovian control tasks with neuroevolution. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1356–1361 (1999)Google Scholar
  15. 15.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  16. 16.
    Gusfield, G.: Algorithms on strings, trees, and sequences. Cambridge University Press, Cambridge (1997)MATHCrossRefGoogle Scholar
  17. 17.
    Igel, C.: Neuroevolution for reinforcement learning using evolution strategies. In: Congress on Evolutionary Computation 2003 (CEC 2003), pp. 2588–2595 (2003)Google Scholar
  18. 18.
    Wieland, A.P.: Evolving neural network controllers for unstable systems. In: Proceedings of the International Joint Conference on Neural Networks, pp. 667–673 (1991)Google Scholar
  19. 19.
    Beer, R.D.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4), 469–509 (1995)CrossRefMathSciNetGoogle Scholar
  20. 20.
    Stanley, K.O.: Efficient evolution of neural networks through complexification. Ph.D. dissertation, University of Texas at Austin (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Peter Dürr
    • 1
  • Claudio Mattiussi
    • 1
  • Dario Floreano
    • 1
  1. 1.Laboratory of Intelligent Systems, Institute of Systems EngineeringEcole Polytechnique Fédérale de LausanneLausanneSwitzerland

Personalised recommendations