Neural Network with Fuzzy Weights Using Type-1 and Type-2 Fuzzy Learning with Gaussian Membership Functions

  • Fernando Gaxiola
  • Patricia Melin
  • Fevrier Valdez
Part of the Studies in Computational Intelligence book series (SCI, volume 547)


In this chapter type-1 and type-2 fuzzy inferences systems are used to obtain the type-1 or type-2 fuzzy weights in the connection between the layers of a neural network. We used two type-1 or type-2 fuzzy systems that work in the backpropagation learning method with the type-1 or type-2 fuzzy weight adjustment. The mathematical analysis of the proposed learning method architecture and the adaptation of type-1 or type-2 fuzzy weights are presented. The proposed method is based on recent methods that handle weight adaptation and especially fuzzy weights. In this work neural networks with type-1 fuzzy weights or type-2 fuzzy weights are presented. The proposed approach is applied to the case of Mackey–Glass time series prediction.


  1. 1.
    Abiyev, R.: A type-2 fuzzy wavelet neural network for time series prediction. Lect. Notes Comput. Sci. 6098, 518–527 (2010)CrossRefGoogle Scholar
  2. 2.
    Barbounis, T.G., Theocharis, J.B.: Locally recurrent neural networks for wind speed prediction using spatial correlation. Inf. Sci. 177(24), 5775–5797 (2007)CrossRefGoogle Scholar
  3. 3.
    Beale, E.M.L.: A derivation of conjugate gradients. In: Lootsma, F.A. (ed.) Numerical Methods for Nonlinear Optimization, pp. 39–43. Academic Press, London (1972)Google Scholar
  4. 4.
    Casasent, D., Natarajan, S.: A classifier neural net with complex-valued weights and square-law nonlinearities. Neural Networks 8(6), 989–998 (1995)CrossRefGoogle Scholar
  5. 5.
    Castillo, O., Melin, P.: A review on the design and optimization of interval type-2 fuzzy controllers. Appl. Soft Comput. 12(4), 1267–1278 (2012)CrossRefGoogle Scholar
  6. 6.
    Castro, J., Castillo, O., Melin, P., Rodríguez-Díaz, A.: A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks. Inf. Sci. 179(13), 2175–2193 (2009)CrossRefMATHGoogle Scholar
  7. 7.
    Castro J., Castillo O., Melin P., Mendoza O., Rodríguez-Díaz A.: An interval type-2 fuzzy neural network for chaotic time series prediction with cross-validation and akaike test. In: Soft Computing for Intelligent Control and Mobile Robotics, pp. 269–285. Springer, Berlin (2011)Google Scholar
  8. 8.
    Cazorla, M., Escolano, F.: Two bayesian methods for junction detection. IEEE Trans. Image Process. 12(3), 317–327 (2003)CrossRefMathSciNetGoogle Scholar
  9. 9.
    De Wilde, O.: The magnitude of the diagonal elements in neural networks. Neural Networks 10(3), 499–504 (1997)CrossRefGoogle Scholar
  10. 10.
    Draghici, S.: On the capabilities of neural networks using limited precision weights. Neural Networks 15(3), 395–414 (2002)CrossRefGoogle Scholar
  11. 11.
    Feuring T.: Learning in fuzzy neural networks. In: IEEE International Conference on Neural Networks, vol. 2, pp. 1061–1066 (1996)Google Scholar
  12. 12.
    Fletcher, R., Reeves, C.M.: Function minimization by conjugate gradients. Comput. J. 7, 149–154 (1964)CrossRefMATHMathSciNetGoogle Scholar
  13. 13.
    Gaxiola, F., Melin, P., Valdez, F., Castillo, O.: Neural network with type-2 fuzzy weights adjustment for pattern recognition of the human iris biometrics. In: MICAI’12 Proceedings of the 11th Mexican International Conference on Advances in Computational Intelligence, vol. 2, pp. 259–270 (2012)Google Scholar
  14. 14.
    Gaxiola, F., Melin, P., Valdez, F., Castillo, O.: Optimization of type-2 fuzzy weight for neural network using genetic algorithm and particle swarm optimization. In: 5th World Congress on Nature and Biologically Inspired Computing, pp. 22–28 (2013)Google Scholar
  15. 15.
    Gaxiola, F., Melin P., Valdez F.: Backpropagation method with type-2 fuzzy weight adjustment for neural network learning. In: Fuzzy Information Processing Society (NAFIPS), Annual Meeting of the North American, pp. 1–6 (2012)Google Scholar
  16. 16.
    Gaxiola, F., Melin, P., Valdez, F.: Genetic optimization of type-2 fuzzy weight adjustment for backpropagation ensemble neural network. In: Recent Advances on Hybrid Intelligent Systems, pp. 159–171 (2013)Google Scholar
  17. 17.
    Gaxiola, F., Melin, P., Valdez, F.: Neural network with lower and upper type-2 fuzzy weights using the backpropagation learning method. In: IFSA World Congress and NAFIPS Annual Meeting (IFSA/NAFIPS), pp. 637–642 (2013)Google Scholar
  18. 18.
    Gedeon, T.: Additive neural networks and periodic patterns. Neural Networks 12(4–5), 617–626 (1999)CrossRefGoogle Scholar
  19. 19.
    Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design, p. 736. PWS Publishing, Boston (1996)Google Scholar
  20. 20.
    Hagras, H.: Type-2 fuzzy logic controllers: a way forward for fuzzy systems in real world environments. In: IEEE World Congress on Computational Intelligence, pp. 181–200 (2008)Google Scholar
  21. 21.
    Ishibuchi, H., Morioka, K., Tanaka, H.: A fuzzy neural network with trapezoid fuzzy weights, fuzzy systems. In: IEEE World Congress on Computational Intelligence, vol. 1, pp. 228–233 (1994)Google Scholar
  22. 22.
    Ishibuchi, H., Tanaka, H., Okada, H.: Fuzzy neural networks with fuzzy weights and fuzzy biases. In: IEEE International Conference on Neural Networks, vol. 3, pp. 1650-1655 (1993)Google Scholar
  23. 23.
    Jang, J.S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, p. 614. Prentice Hall, Englewood Cliffs (1997)Google Scholar
  24. 24.
    Kamarthi, S., Pittner, S.: Accelerating neural network training using weight extrapolations. Neural Networks 12(9), 1285–1299 (1999)CrossRefGoogle Scholar
  25. 25.
    Karnik, N., Mendel, J.: Applications of type-2 fuzzy logic systems to forecasting of time-series. Inf. Sci. 120(1–4), 89–111 (1999)CrossRefMATHGoogle Scholar
  26. 26.
    Martinez, G., Melin, P., Bravo, D., Gonzalez, F., Gonzalez, M.: Modular neural networks and fuzzy sugeno integral for face and fingerprint recognition. Adv. Soft Comput. 34, 603–618 (2006)Google Scholar
  27. 27.
    Melin, P.: Modular Neural Networks and Type-2 Fuzzy Systems for Pattern Recognition, pp. 1–204. Springer, Berlin (2012)CrossRefMATHGoogle Scholar
  28. 28.
    Meltser, M., Shoham, M., Manevitz, L.: Approximating functions by neural networks: a constructive solution in the uniform norm. Neural Networks 9(6), 965–978 (1996)CrossRefGoogle Scholar
  29. 29.
    Moller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6, 525–533 (1993)CrossRefGoogle Scholar
  30. 30.
    Monirul Islam, M.D., Murase, K.: A new algorithm to design compact two-hidden-layer artificial neural networks. Neural Networks 14(9), 1265–1278 (2001)CrossRefGoogle Scholar
  31. 31.
    Neville, R.S., Eldridge, S.: Transformations of sigma–pi nets: obtaining reflected functions by reflecting weight matrices. Neural Networks 15(3), 375–393 (2002)CrossRefGoogle Scholar
  32. 32.
    Phansalkar, V.V., Sastry, P.S.: Analysis of the back-propagation algorithm with momentum. IEEE Trans. Neural Networks 5(3), 505–506 (1994)CrossRefGoogle Scholar
  33. 33.
    Powell, M.J.D.: Restart procedures for the conjugate gradient method. Math. Program. 12, 241–254 (1977)CrossRefMATHGoogle Scholar
  34. 34.
    Salazar, P.A., Melin, P., Castillo, O.: A new biometric recognition technique based on hand geometry and voice using neural networks and fuzzy logic. In: Soft Computing for Hybrid Intelligent Systems, pp. 171–186 (2008)Google Scholar
  35. 35.
    Sepúlveda, R., Castillo, O., Melin, P. Montiel, O.: An efficient computational method to implement type-2 fuzzy logic in control applications. In: Analysis and Design of Intelligent Systems using Soft Computing Techniques, pp. 45–52 (2007)Google Scholar
  36. 36.
    Yam, J., Chow, T.: A weight initialization method for improving training speed in feedforward neural network. Neurocomputing 30(1–4), 219–232 (2000)CrossRefGoogle Scholar
  37. 37.
    Yeung, D., Chan, P., Ng, W.: Radial basis function network learning using localized generalization error bound. Inf. Sci. 179(19), 3199–3217 (2009)CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Fernando Gaxiola
    • 1
  • Patricia Melin
    • 1
  • Fevrier Valdez
    • 1
  1. 1.Tijuana Institute of TechnologyTijuanaMexico

Personalised recommendations