Evolving Stochastic Learning Algorithm based on Tsallis entropic index



In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and stochastic search steps by employing a different adaptive stepsize for each network weight, and applies a form of noise that is characterized by the nonextensive entropic index q, regulated by a weight decay term. The behavior of the learning algorithm can be made more stochastic or deterministic depending on the trade off between the temperature T and the q values. This is achieved by introducing a formula that defines a time-dependent relationship between these two important learning parameters. Our experimental study verifies that there are indeed improvements in the convergence speed of this new evolving stochastic learning algorithm, which makes learning faster than using the original Hybrid Learning Scheme (HLS). In addition, experiments are conducted to explore the influence of the entropic index q and temperature T on the convergence speed and stability of the proposed method.


07.05.Mh Neural networks, fuzzy logic, artificial intelligence 87.18.Sn Neural networks 05.10.-a Computational methods in statistical physics and nonlinear dynamics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. S. Haykin, Neural Networks: A Comprehensive Foundation (Macmillan College Publishing Company, 1994) Google Scholar
  2. G. Gyorgyi, Physics Reports 342, issue 4–5, 263 (2001) Google Scholar
  3. S. Kirkpatrick, C.D. Gelatt Jr., M.P. Vecchi, Science 220, 671 (1983) ADSMathSciNetGoogle Scholar
  4. D. Ackley, G. Hinton, T. Sejnowski, Cogn. Sci. 9, 147 (1985) CrossRefGoogle Scholar
  5. E.H.L. Arts, J. Korst, Simulated Annealing and Boltzmann Machines (Wiley, New York, 1989) Google Scholar
  6. R.M. Burton, G.J. Mpitsos, Neural Networks 5, 627 (1992) CrossRefGoogle Scholar
  7. T. Rögnvaldsson, Neural Computation 6, 916 (1994) MATHGoogle Scholar
  8. N.K. Treadgold, T.D. Gedeon, IEEE Tr. Neural Networks 9, 4, 662 (1998) Google Scholar
  9. A.D. Anastasiadis, G.D. Magoulas, Physica A 344, 372 (2004) CrossRefADSGoogle Scholar
  10. M. Riedmiller, H. Braun, A direct adaptive method for faster backpropagation learning: The Rprop algorithm, Proc. Int. Conf. Neur. Net. (San Francisco, CA, 1993), pp. 586–591 Google Scholar
  11. C. Tsallis, D.A. Stariolo, Physica A 233, 395 (1996) CrossRefADSGoogle Scholar
  12. C. Tsallis, J. Stat. Phys. 52, 479 (1988) CrossRefMATHMathSciNetGoogle Scholar
  13. H. Szu, Nonconvex optimization by fast simulated annealing, Proceedings of IEEE, Vol. 75 (1987), pp. 1538–1540 Google Scholar
  14. G. Snedecor, W. Cochran, Statistical Methods, 8th edn. (Iowa State University Press, 1989) Google Scholar
  15. L. Prechelt, PROBEN1–A set of benchmarks and benchmarking rules for neural network training algorithms, Technical report 21/94, Fakultät für Informatik, Universität Karlsruhe, 1994 Google Scholar
  16. P.M. Murphy, D.W. Aha, UCI Repository of machine learning databases, mlearn/MLRepository.html, 1994 Google Scholar
  17. M.V. Boland, R.F. Murphy, IEEE Engineering in Medicine and Biology, Sept./Oct. (1999), pp. 115–119 Google Scholar
  18. H. Lodish, A. Berk, S.L. Zipursky, P. Matsudaira, D. Baltimore, J. James Darnell, Molecular Cell Biology, 5th edn. (Freeman, 2003) Google Scholar
  19. P. Horton, K. Nakai, Better Prediction of Protein Cellular Localization Sites with the k Nearest Neighbors Classifier, Proc. of Intelligent Systems in Molecular Biology (1997), pp. 368–383 Google Scholar
  20. A.D. Anastasiadis, G.D. Magoulas, X. Liu, Classification of protein localisation patterns via supervised neural network learning, Proc. of the Fifth Symposium on Intelligent Data Analysis, Lecture Notes in Computer Science 2810, (Springer-Verlag, 2003), pp. 430–439 Google Scholar
  21. R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, International Joint Conference on Artificial Intelligence (1995), pp. 223–228 Google Scholar
  22. E.K. Blum, Neural Computation 1, 532 (1989) Google Scholar

Copyright information

© EDP Sciences/Società Italiana di Fisica/Springer-Verlag 2006

Authors and Affiliations

  1. 1.School of Computer Science and Information Systems, Birkbeck College, University of LondonLondonUK

Personalised recommendations