Improving the Performance of NEAT Related Algorithm via Complexity Reduction in Search Space

  • Heman MohabeerEmail author
  • K. M. S. Soyjaudah
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 217)


In this paper, we focus on the learning aspect of NEAT and its variants in an attempt to solve benchmark problems through fewer generations. In NEAT, genetic algorithm is the key technique that is used to complexify artificial neural network. Crossover value, being the parameter that dictates the evolution of NEAT is reduced. Reducing crossover rate aids in allowing the algorithm to learn. This is because lesser interchange among genes ensures that patterns of genes carrying valuable information is not split or strayed during mating of two chromosomes. By tweaking the crossover parameter and with some minor modification, it is shown that the performance of NEAT can be improved. This enables NEAT algorithm to evolve slowly and retain information even while undergoing complexification. Thus, the learning process in NEAT is greatly enhanced as compared to evolution.


Crossover NEAT Learning Evolution Genetic algorithm artificial neural network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Stanley, K.O., Miikkulainen, R.: Efficient Evolution of Neural Network Topologies. In: Proceedings of the 2002 Congress on Evolutionary Computation (CEC 2002), Honolulu, Hawaii (2002)Google Scholar
  2. 2.
    Gomez, F., Miikkulainen, R.: Solving non-Markovian control tasks with neuroevolution. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Denver (1999)Google Scholar
  3. 3.
    Moriarty, D.E.: Symbiotic Evolution of Neural Networks in Sequential Decision Tasks. PhD thesis, Department of Computer Sciences, The University of Texas at Austin, Technical Report UT-AI97-257 (1997)Google Scholar
  4. 4.
    Zheng, Z.: A benchmark for classifier learning. Technical Report TR474, Basser Department of Computer Science, University of Sydney, N.S.W. Australia (2006), Anonymous ftp from
  5. 5.
    Granville, V., Krivanek, M., Rasson, J.P.: Simulated annealing: A proof of convergence. IEEE Transactions on Pattern Analysis and Machine Intelligence 16(6), 652–656 (1994)CrossRefGoogle Scholar
  6. 6.
    Cano, A., Gomez, M., Moral, S.: Application of a hill-climbing algorithm to exact and approximate inference in credal networks. In: 4th International Symposium on Imprecise Probabilities and Their Applications, Pittsburgh, Pennsylvania (2005)Google Scholar
  7. 7.
    Stanley, K.O.: Exploiting Regularity without Development. In: Proceedings of the 2006 AAAI Fall Symposium on Developmental Systems. AAAI Press, Menlo Park (2006)Google Scholar
  8. 8.
    Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. Journal of Artificial Intelligence Research 21, 63–100 (2004)Google Scholar
  9. 9.
    Whiteson, S., Stanley, K.O., Miikkulainen, R.: Automatic Feature Selection in Neuroevolution. In: Proceedings of the Genetic and Evolutionary Computation Conference Workshop on Self-Organization (GECCO 2004), Seattle, WA (2004)Google Scholar
  10. 10.
  11. 11.
    Moriarty, D.E., Miikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Machine Learning 22, 11–32 (1996)Google Scholar
  12. 12.
    Baird, L.C.: Residual Algorithms: Reinforcement Learning with Function Approximation. In: Prieditis, A., Russell, S. (eds.) Proceedings of the Twelfth International Conference on Machine Learning, July 9-12 (1995)Google Scholar
  13. 13.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  14. 14.

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  1. 1.Department of Electrical and Electronics EngineeringUniversity of MauritiusReduitMauritius

Personalised recommendations