Credit Assignment Among Neurons in Co-evolving Populations

  • Vineet R. Khare
  • Xin Yao
  • Bernhard Sendhoff
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3242)

Abstract

Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem).

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Potter, M.A., Jong, K.A.D.: Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents. Evolutionary Computation 8, 1–29 (2000)CrossRefGoogle Scholar
  2. 2.
    Yong, C.H., Miikkulainen, R.: Cooperative Coevolution of Multi-Agent Systems. Technical Report AI01-287, Department of computer Sciences, The University of Texas at Austin, Austin, TX 78712 USA (2001)Google Scholar
  3. 3.
    Smalz, R., Conrad, M.: Combining Evolution With Credit Apportionment: A New Learning Algorithm for Neural Nets. Neural Networks 7, 341–351 (1994)CrossRefGoogle Scholar
  4. 4.
    Moriarty, D.E., Miikkulainen, R.: Forming Neural Networks Through Efficient and Adaptive Coevolution. Evolutionary Computation 5, 373–399 (1997)CrossRefGoogle Scholar
  5. 5.
    Igel, C., Hüsken, M.: Empirical Evaluation of the Improved Rprop Learning Algorithm. Neurocomputing 50, 105–123 (2003)MATHCrossRefGoogle Scholar
  6. 6.
    Riedmiller, M., Braun, H.: A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP algorithm. In: Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, pp. 586–591 (1993)Google Scholar
  7. 7.
    Whitehead, B.A., Choate, T.D.: Cooperative-Competitive Genetic Evolution of Radial Basis Function Centers and Widths for Time Series Prediction. IEEE Transactions on Neural Networks 7, 869–880 (1996)CrossRefGoogle Scholar
  8. 8.
    Whitehead, B.A.: Genetic Evolution of Radial Basis Function Coverage Using Orthogonal Niches. IEEE Transactions on Neural Networks 7, 1525–1528 (1996)CrossRefGoogle Scholar
  9. 9.
    Hüsken, M., Gayko, J.E., Sendhoff, B.: Optimization for Problem Classes - Neural Networks that Learn to Learn. In: Yao, X. (ed.) IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks, pp. 98–109. IEEE Press, Los Alamitos (2000)CrossRefGoogle Scholar
  10. 10.
    Blake, C., Merz, C.: UCI Repository of machine learning databases (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html
  11. 11.
    Khare, V., Yao, X.: Artificial Speciation and Automatic Modularisation. In: Wang, L., Tan, K.C., Furuhashi, T., Kim, J.H., Yao, X. (eds.) Proceedings of the 4th Asia- Pacific Conference on Simulated Evolution And Learning (SEAL 2002), Singapore, vol. 1, pp. 56–60 (2002)Google Scholar
  12. 12.
    Yao, X., Liu, Y.: Making Use of Population Information in Evolutionary Artificial Neural Networks. IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics 28, 417–425 (1998)Google Scholar
  13. 13.
    Yao, X., Liu, Y.: A New Evolutionary System for Evolving Artificial Neural Networks. IEEE Transactions on Neural Networks 8, 694–713 (1997)CrossRefGoogle Scholar
  14. 14.
    Farmer, J.D., Sidorowich, J.J.: Predicting chaotic time series. Physical Review Letters 59, 845–848 (1987)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Mackey, M.C., Glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1977)CrossRefGoogle Scholar
  16. 16.
    Martinetz, T.M., Berkovich, S.G., Schulten, K.J.: ‘Neural-Gas’ Network for Vector Quantization and its Application to Time-Series Prediction. IEEE Transactions on Neural Networks 4, 558–569 (1993)CrossRefGoogle Scholar
  17. 17.
    Bishop, C.M.: Neural Networks for Pattern Recogntion. Oxford University Press, Oxford (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Vineet R. Khare
    • 1
  • Xin Yao
    • 1
  • Bernhard Sendhoff
    • 2
  1. 1.Natural Computation Group, School of Computer ScienceThe University of BirminghamBirminghamUK
  2. 2.Honda Research Institute Europe GmbHOffenbach/MainGermany

Personalised recommendations