Advertisement

Reverse Neuron Level Decomposition for Cooperative Neuro-Evolution of Feedforward Networks for Time Series Prediction

  • Ravneil NandEmail author
  • Rohitash Chandra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9592)

Abstract

A major challenge in cooperative neuro-evolution is to find an efficient problem decomposition that takes into account architectural properties of the neural network and the training problem. In the past, neuron and synapse Level decomposition methods have shown promising results for time series problems, howsoever, the search for the optimal method remains. In this paper, a problem decomposition method, that is based on neuron level decomposition is proposed that features a reverse encoding scheme. It is used for training feedforward networks for time series prediction. The results show that the proposed method has improved performance when compared to related problem decomposition methods and shows competitive results when compared to related methods in the literature.

Keywords

Cooperative coevolution Feedforward networks Problem decomposition Time series prediction 

References

  1. 1.
    Stephen, H.K.: In the Wake of Chaos: Unpredictable Order in Dynamical Systems. University of Chicago Press, Chicago (1993)zbMATHGoogle Scholar
  2. 2.
    Parras-Gutierrez, E., Rivas, V., Garcia-Arenas, M., del Jesus, M.: Short, medium and long term forecasting of time series using the L-Co-R algorithm. Neurocomputing 128, 433–446 (2014). http://www.sciencedirect.com/science/article/pii/S0925231213008990 CrossRefGoogle Scholar
  3. 3.
    Chandra, R., Zhang, M.: Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction. Neurocomputing 186, 116–123 (2012)CrossRefGoogle Scholar
  4. 4.
    Potter, M., De Jong, K.: A cooperative coevolutionary approach to function optimization. In: Davidor, Y., Schwefel, H.-P., Mnner, R. (eds.) Parallel Problem Solving from Nature PPSN III. LNCS, vol. 866, pp. 249–257. Springer, Berlin Heidelberg (1994)CrossRefGoogle Scholar
  5. 5.
    Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated neural evolution through cooperatively coevolved synapses. J. Mach. Learn. Res. 9, 937–965 (2008)MathSciNetzbMATHGoogle Scholar
  6. 6.
    García-Pedrajas, N., Ortiz-Boyer, D.: A cooperative constructive method for neural networks for pattern recognition. Pattern Recogn. 40(1), 80–98 (2007)CrossRefzbMATHGoogle Scholar
  7. 7.
    Chandra, R., Frean, M.R., Zhang, M.: Crossover-based local search in cooperative co-evolutionary feedforward neural networks. Appl. Soft Comput. 12(9), 2924–2932 (2012)CrossRefGoogle Scholar
  8. 8.
    Gomez, F., Mikkulainen, R.: Incremental evolution of complex general behavior. Adapt. Behav. 5(3–4), 317–342 (1997)CrossRefGoogle Scholar
  9. 9.
    Chandra, R., Frean, M., Zhang, M.: On the issue of separability for problem decomposition in cooperative neuro-evolution. Neurocomputing 87, 33–40 (2012)CrossRefGoogle Scholar
  10. 10.
    Chandra, R., Frean, M., Zhang, M.: An encoding scheme for cooperative coevolutionary feedforward neural networks. In: Li, J. (ed.) AI 2010. LNCS, vol. 6464, pp. 253–262. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  11. 11.
    Mackey, M., Glass, L.: Oscillation and chaos in physiological control systems. Science 197(4300), 287–289 (1977)CrossRefGoogle Scholar
  12. 12.
    Lorenz, E.: Deterministic non-periodic flows. J. Atmos. Sci. 20, 267–285 (1963)Google Scholar
  13. 13.
    SILSO World Data Center, The International Sunspot Number (1834–2001), International Sunspot Number Monthly Bulletin and Online Catalogue, Royal Observatory of Belgium, Avenue Circulaire 3, 1180 Brussels, Belgium (2015). Accessed on 02 February 2015. http://www.sidc.be/silso/
  14. 14.
    NASDAQ Exchange Daily: 1970–2010 Open, Close, High, Low and Volume (2015). Accessed on 02 February 2015. http://www.nasdaq.com/symbol/aciw/stock-chart
  15. 15.
    Takens, F.: Detecting strange attractors in turbulence. In: Rand, D., Young, L.-S. (eds.) Dynamical Systems and Turbulence, Warwick 1980. LNCS, vol. 898, pp. 366–381. Springer, Heidelberg (1995) CrossRefGoogle Scholar
  16. 16.
    Sello, S.: Solar cycle forecasting: a nonlinear dynamics approach. Astron. Astrophys. 377, 312–320 (2001)CrossRefGoogle Scholar
  17. 17.
    Deb, K., Anand, A., Joshi, D.: A computationally efficient evolutionary algorithm for real-parameter optimization. Evol. Comput. 10(4), 371–395 (2002)CrossRefGoogle Scholar
  18. 18.
    Gholipour, A., Araabi, B.N., Lucas, C.: Predicting chaotic time series using neural and neurofuzzy models: a comparative study. Neural Process. Lett. 24, 217–239 (2006)CrossRefGoogle Scholar
  19. 19.
    Lin, C.-J., Chen, C.-H., Lin, C.-T.: A hybrid of cooperative particle swarm optimization and cultural algorithm for neural fuzzy networks and its prediction applications. IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev. 39(1), 55–68 (2009)CrossRefGoogle Scholar
  20. 20.
    Chandra, R.: Competition and collaboration in cooperative coevolution of Elman recurrent neural networks for time-series prediction. IEEE Transactions onNeural Networks and Learning Systems (2015). (In Press)Google Scholar
  21. 21.
    Rojas, I., Valenzuela, O., Rojas, F., Guillen, A., Herrera, L., Pomares, H., Marquez, L., Pasadas, M.: Soft-computing techniques and arma model for time series prediction. Neurocomputing 71(4–6), 519–537 (2008)CrossRefGoogle Scholar
  22. 22.
    Ardalani-Farsa, M., Zolfaghari, S.: Residual analysis and combination of embedding theorem and artificial intelligence in chaotic time series forecasting. Appl. Artif. Intell. 25, 45–73 (2011)CrossRefGoogle Scholar
  23. 23.
    Chandra, R.: Competitive two-island cooperative coevolution for training Elman recurrent networks for time series prediction. In: International Joint Conference on Neural Networks (IJCNN), Beijing, China, pp. 565–572, July 2014Google Scholar
  24. 24.
    Chand, S., Chandra, R.: Cooperative coevolution of feed forward neural networks for financial time series problem. In: International Joint Conference on Neural Networks (IJCNN), Beijing, China, pp. 202–209, July 2014Google Scholar
  25. 25.
    Chand, S., Chandra, R.: Multi-objective cooperative coevolution of neural networks for time series prediction. In: International Joint Conference on Neural Networks (IJCNN), Beijing, China, pp. 190–197. July 2014Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.School of Computing Information and Mathematical SciencesUniversity of South PacificSuvaFiji

Personalised recommendations