Advertisement

Complex-Valued Multilayer Perceptron Search Utilizing Eigen Vector Descent and Reducibility Mapping

  • Shinya Suzumura
  • Ryohei Nakano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7553)

Abstract

A complex-valued multilayer perceptron (MLP) can approximate a periodic or unbounded function, which cannot be easily realized by a real-valued MLP. Its search space is full of crevasse-like forms having huge condition numbers; thus, it is very hard for existing methods to perform efficient search in such a space. The space also includes the structure of reducibility mapping. The paper proposes a new search method for a complex-valued MLP, which employs both eigen vector descent and reducibility mapping, aiming to stably find excellent solutions in such a space. Our experiments showed the proposed method worked well.

Keywords

complex-valued multilayer perceptron Wirtinger calculus search method eigen vector reducibility mapping 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Amin, M. F., Amin, M.I., Al-Nuaimi, A.Y.H., Murase, K.: Wirtinger Calculus Based Gradient Descent and Levenberg-Marquardt Learning Algorithms in Complex-Valued Neural Networks. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011, Part I. LNCS, vol. 7062, pp. 550–559. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  2. 2.
    Delgado, K.K.: The complex gradient operator and the CR-calculus. ECE275A-Lecture Supplement, Fall (2006)Google Scholar
  3. 3.
    Fukumizu, K., Amari, S.: Local minima and plateaus in hierarchical structure of multilayer perceptrons. Neural Networks 13(3), 317–327 (2000)CrossRefGoogle Scholar
  4. 4.
    Kim, T., Adali, T.: Approximation by fully complex multilayer perceptrons. Neural Computation 15(7), 1641–1666 (2003)CrossRefzbMATHGoogle Scholar
  5. 5.
    Kuroe, Y., Yoshida, M., Mori, T.: On Activation Functions for Complex-Valued Neural Networks–Existence of Energy Functions. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 985–992. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  6. 6.
    Luenberger, D.G.: Linear and nonlinear programming. Addison-Wesley (1984)Google Scholar
  7. 7.
    Leung, H., Haykin, S.: The complex backpropagation algorithm. IEEE Trans. Signal Processing 39(9), 2101–2104 (1991)CrossRefGoogle Scholar
  8. 8.
    Nakano, R., Satoh, S., Ohwaki, T.: Learning method utilizing singular region of multilayer perceptron. In: Proc. 3rd Int. Conf. on Neural Computation Theory and Applications, pp. 106–111 (2011)Google Scholar
  9. 9.
    Nitta, T.: Reducibility of the complex-valued neural network. Neural Information Processing - Letters and Reviews 2(3), 53–56 (2004)Google Scholar
  10. 10.
    Sussmann, H.J.: Uniqueness of the weights for minimal feedforward nets with a given input-output map. Neural Networks 5(4), 589–593 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Shinya Suzumura
    • 1
  • Ryohei Nakano
    • 1
  1. 1.Chubu UniversityKasugaiJapan

Personalised recommendations