Impact of Weight Initialization on Multilayer Perceptron Using Fuzzy Similarity Quality Measure

  • Lenniet CoelloEmail author
  • Yumilka Fernández
  • Yaima Filiberto
  • Rafael Bello
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 657)


This paper presents an algorithm for initializing the weights in multilayer perceptrons based on the new metrics called Fuzzy Similarity Quality. The new metric used a binary fuzzy relation for quantify the strength of the similarity between two objects. This measure computes the grade of similarity in a decision system in which the features can have discrete or continuous values. Experimental results show that the proposed initialization method performs better than other previously reported methods to calculate the weight of features.


Fuzzy Similarity Quality Measure Multilayer perceptrons Weight of features 


  1. 1.
    Filiberto, Y., Bello, R., Caballero, Y., Larrua, R.: A method to build similarity relations into extended rough set theory. In: 10th International Conference on Intelligent Systems Design and Applications, pp. 1314–1319 (2010)Google Scholar
  2. 2.
    Verdegay, J.L., Yager, R.R., Bonissone, P.P.: On heuristics as a fundamental component of soft computing. J. Fuzzy Sets Syst. 159, 846–855 (2008)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Fu, X., Zhang, S., Pang, Z.: A resource limited immune approach for evolving architecture and weights of multilayer neural network. In: Tan, Y., Shi, Y., Tan, K.C. (eds.) ICSI 2010, Part I. LNCS, vol. 6145, pp. 328–337. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Adam, S., Karras, D.A., Vrahatis, M.N.: Revisiting the problem of weight initialization for multi-layer perceptrons trained with back propagation. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008. LNCS, vol. 5507, pp. 308–315. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-03040-6_38 CrossRefGoogle Scholar
  5. 5.
    Coello, L., Fernandez, Y., Filiberto, Y., Bello, R.: Improving the MLP learning by using a method to calculate the initial weights with the quality of similarity measure based on fuzzy sets and particle swarms. J. Computación y Sistemas 19, 1–12 (2015)Google Scholar
  6. 6.
    Filiberto, Y., Bello, R., Caballero, Y., Larrua, R.: Using PSO and RST to predict the resistant capacity of connections in composite structures. In: González, J.R., Pelta, D.A., Cruz, C., Terrazas, G., Krasnogor, N. (eds.) NICSO 2010. SCI, vol. 284, pp. 359–370. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Fernandez, Y., Coello, L., Filiberto, Y., Bello, R., Falco, R.: Learning similarity measures from data with fuzzy sets and particle swarms. In: 11th International Conference on Electrical Engineering, Computing Science and Automatic Control, pp. 1–6. IEEE Press, Mexico (2014)Google Scholar
  8. 8.
    Filiberto, Y., Bello, R., Caballero, Y., Frias, M.: An analysis about the measure quality of similarity and its applications in machine learning. In: 4th International Workshop on Knowledge Discovery, Knowledge Management and Decision Support, pp. 130–139, Mexico (2013)Google Scholar
  9. 9.
    Zadeh, L.A.: Similarity relations and fuzzy orderings. Inf. Sci. 3, 177–200 (1971)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Wang, W.: New similarity measures on fuzzy sets and on elements. J. Fuzzy Sets Syst. 85, 305–309 (1997)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Iman, R., Davenport, J.: Approximations of the critical region of the Friedman statistic. Commun. Stat. Part A Theor. Meth. 9, 571–595 (1980)CrossRefzbMATHGoogle Scholar
  12. 12.
    Holm, S.: A simple sequentially rejective multiple test procedure. J. Stat. 6, 65–70 (1979)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Lenniet Coello
    • 1
    Email author
  • Yumilka Fernández
    • 1
  • Yaima Filiberto
    • 1
  • Rafael Bello
    • 2
  1. 1.Department of Computer ScienceUniversidad de CamagüeyCamagüeyCuba
  2. 2.Department of Computer ScienceUniversidad Central de Las VillasSanta ClaraCuba

Personalised recommendations