Parallel Approach to the Levenberg-Marquardt Learning Algorithm for Feedforward Neural Networks

  • Jarosław Bilski
  • Jacek Smoląg
  • Jacek M. Żurada
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9119)

Abstract

A parallel architecture of the Levenberg-Marquardt algorithm for training a feedforward neural network is presented. The proposed solution is based on completely new parallel structures to effectively reduce high computational load of this algorithm. Detailed parallel neural network structures are explicitely discussed.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bilski, J.: The UD RLS algorithm for training the feedforward neural networks. International Journal of Applied Mathematics and Computer Science 15(1), 101–109 (2005)Google Scholar
  2. 2.
    Bilski, J., Litwiński, S., Smoląg, J.: Parallel realisation of QR algorithm for neural networks learning. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 158–165. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Bilski, J., Smoląg, J.: Parallel realisation of the recurrent RTRN neural network learning. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 11–16. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Bilski, J., Smoląg, J.: Parallel realisation of the recurrent Elman neural network learning. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS (LNAI), vol. 6114, pp. 19–25. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Bilski, J., Smoląg, J.: Parallel realisation of the recurrent multi layer perceptron learning. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS (LNAI), vol. 7267, pp. 12–20. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  6. 6.
    Bilski, J., Smoląg, J.: Parallel approach to learning of the recurrent Jordan neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS (LNAI), vol. 7894, pp. 32–40. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  7. 7.
    Bilski, J.: Parallel Structures for Feedforward and Dynamical Neural Networks (in Polish). AOW EXIT (2013)Google Scholar
  8. 8.
    Bilski, J., Smoląg, J., Galushkin, A.I.: The parallel approach to the conjugate gradient learning algorithm for the feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014, Part I. LNCS (LNAI), vol. 8467, pp. 12–21. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  9. 9.
    Bilski, J., Smoląg, J.: Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks. IEEE Transactions on Parallel and Distributed Systems PP(99) (2014), doi:10.1109/TPDS.2014.2357019Google Scholar
  10. 10.
    Chu, J.L., Krzyźak, A.: The recognition of partially occluded objects with support vector machines, convolutional neural networks and deep belief networks. Journal of Artificial Intelligence and Soft Computing Research 4(1), 5–19 (2014)CrossRefGoogle Scholar
  11. 11.
    Cpałka, K., Rutkowski, L.: Flexible Takagi-Sugeno Fuzzy Systems. In: Proceedings of the Int. Joint Conference on Neural Networks, Montreal, pp. 1764–1769 (2005)Google Scholar
  12. 12.
    Cpałka, K., Łapa, K., Przybył, A., Zalasiński, M.: A new method for designing neuro-fuzzy systems for nonlinear modelling with interpretability aspects. Neurocomputing 135, 203–217 (2014)CrossRefGoogle Scholar
  13. 13.
    Cpalka, K., Rebrova, O., Nowicki, R., et al.: On design of flexible neuro-fuzzy systems for nonlinear modelling. International Journal of General Systems 42(6), Special Issue: SI, 706–720 (2013)Google Scholar
  14. 14.
    Fahlman, S.: Faster learning variations on backpropagation: An empirical study. In: Proceedings of Connectionist Models Summer School, Los Atos (1988)Google Scholar
  15. 15.
    Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 5(6), 989–993 (1994)CrossRefGoogle Scholar
  16. 16.
    Korytkowski, M., Nowicki, R., Rutkowski, L., Scherer, R.: AdaBoost Ensemble of DCOG Rough–Neuro–Fuzzy Systems. In: Jędrzejowicz, P., Nguyen, N.T., Hoang, K. (eds.) ICCCI 2011, Part I. LNCS, vol. 6922, pp. 62–71. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  17. 17.
    Korytkowski, M., Rutkowski, L., Scherer, R.: From ensemble of fuzzy classifiers to single fuzzy rule base classifier. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 265–272. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  18. 18.
    Korytkowski, M., Scherer, R.: Negative Correlation Learning of Neuro-fuzzy System Ensembles. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part I. LNCS (LNAI), vol. 6113, pp. 114–119. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  19. 19.
    Laskowski, L., Jelonkiewicz, J.: Self-Correcting Neural Network for stereo-matching problem solving. Fundamenta Informaticae 138, 1–26 (2015)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Łapa, K., Przybył, A., Cpałka, K.: A new approach to designing interpretable models of dynamic systems. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part II. LNCS (LNAI), vol. 7895, pp. 523–534. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  21. 21.
    Łapa, K., Zalasiński, M., Cpałka, K.: A new method for designing and complexity reduction of neuro-fuzzy systems for nonlinear modelling. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS (LNAI), vol. 7894, pp. 329–344. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  22. 22.
    Marqardt, D.: An algorithm for last-sqares estimation of nonlinear paeameters. J. Soc. Ind. Appl. Math., 431–441 (1963)Google Scholar
  23. 23.
    Patan, K., Patan, M.: Optimal training strategies for locally recurrent neural networks. Journal of Artificial Intelligence and Soft Computing Research 1(2), 103–114 (2011)Google Scholar
  24. 24.
    Riedmiller, M., Braun, H.: A direct method for faster backpropagation learning: The RPROP Algorithm. In: IEEE International Conference on Neural Networks, San Francisco (1993)Google Scholar
  25. 25.
    Romaszewski, M., Gawron, P., Opozda, S.: Dimensionality reduction of dynamic msh animations using HO-SVD. Journal of Artificial Intelligence and Soft Computing Research 3(3), 277–289 (2013)Google Scholar
  26. 26.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McCelland, J. (red.) Parallel Distributed Processing, ch. 8, vol. 1. The MIT Press, Cambridge (1986)Google Scholar
  27. 27.
    Rutkowski, L.: Multiple Fourier series procedures for extraction of nonlinear regressions from noisy data. IEEE Transactions on Signal Processing 41(10), 3062–3065 (1993)CrossRefGoogle Scholar
  28. 28.
    Rutkowski, L.: Identification of MISO nonlinear regressions in the presence of a wide class of disturbances. IEEE Transactions on Information Theory 37(1), 214–216 (1991)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: Decision trees for mining data streams based on the gaussian approximation. IEEE Transactions on Knowledge and Data Engineering 26(1), 108–119 (2014)CrossRefGoogle Scholar
  30. 30.
    Rutkowski, L., Przybył, A., Cpałka, K., Er, M.J.: Online speed profile generation for industrial machine tool based on neuro-fuzzy approach. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS (LNAI), vol. 6114, pp. 645–650. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  31. 31.
    Rutkowski, L., Rafajlowicz, E.: On optimal global rate of convergence of some nonparametric identification procedures. IEEE Transactions on Automatic Control 34(10), 1089–1091 (1989)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Smoląg, J., Bilski, J.: A systolic array for fast learning of neural networks. In: Proc. of V Conf. Neural Networks and Soft Computing, Zakopane, pp. 754–758 (2000)Google Scholar
  33. 33.
    Smoląg, J., Rutkowski, L., Bilski, J.: Systolic array for neural networks. In: Proc. of IV Conf. Neural Networks and Their Applications, Zakopane, pp. 487–497 (1999)Google Scholar
  34. 34.
    Starczewski, A.: A clustering method based on the modified RS validity index. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part II. LNCS (LNAI), vol. 7895, pp. 242–250. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  35. 35.
    Starczewski, J., Rutkowski, L.: Connectionist structures of type 2 Fuzzy Inference Systems. In: 4th International Conference on Parallel Processing and Applied Mathematics, Nalenczow, Poland (2001)Google Scholar
  36. 36.
    Starczewski, J., Rutkowski, L.: Interval type 2 neuro-fuzzy systems based on interval consequents. In: Neural Networks and Soft Computing. Advances In Soft Computing, pp. 570–577 (2003)Google Scholar
  37. 37.
    Tadeusiewicz, R.: Neural Networks (in Polish). AOW RM (1993)Google Scholar
  38. 38.
    Werbos, J.: Backpropagation through time: What it does and how to do it. Proceedings of the IEEE 78(10) (1990)Google Scholar
  39. 39.
    Wilamowski, B.M., Yo, H.: Neural network learning without backpropagation. IEEE Transactions on Neural Networks 21(11), 1793–1803 (2010)CrossRefGoogle Scholar
  40. 40.
    Zalasiński, M., Cpałka, K.: New approach for the on-line signature verification based on method of horizontal partitioning. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part II. LNCS (LNAI), vol. 7895, pp. 342–350. Springer, Heidelberg (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Jarosław Bilski
    • 1
  • Jacek Smoląg
    • 1
  • Jacek M. Żurada
    • 2
    • 3
  1. 1.Institute of Computational IntelligenceCzȩstochowa University of TechnologyCzȩstochowaPoland
  2. 2.Information Technology InstituteUniversity of Sociel SciencesŁódźPoland
  3. 3.Department Electrical and Computer EngineeringUniversity of LouisvilleLouisvilleUSA

Personalised recommendations