The Behavior of the Complex Integral Neural Network

  • Pan Yong
  • Shi Hongbao
  • Li Lei
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2005)

Abstract

In this paper, we introduce an Integral Neural Network based on complex domain. We describe the model of the neuron, analyze the behavior of the neuron, and indicate that in certain conditions it performs the calculation of Fourier Integration. Have studied on the neural network with hidden layers, we obtain the following facts: 1. This kind of structure can memorize a time variant function; 2. It calculates the convolution of input series and the function the neural network memorized; 3. This neural network structure also can calculate the correlation function; 4. In the case of many hidden layers, it can perform the Fourier Transform with many variants.

Keywords

Neural Network Hide Layer Discrete Fourier Transform Input Function Complex Domain 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Reference

  1. 1.
    Iku Nemoto, Makoto Kubono, “Complex Associative Memory”, Neural Networks, Vol. 9, No. 2 (1996) 253–261.CrossRefGoogle Scholar
  2. 2.
    T. Nitta, “An Extension of the Back-Propagation Algorithm to Complex Numbers”, Neural Networks, Vol. 9, No. 2 (1996) 1392–1414Google Scholar
  3. 3.
    Stanislaw Jankowski, andrzej Lozowski, and Jacek M. Zurada, “Complex-Valued Multistate Neural Associative Memory”, IEEE Trans, on Neural Networks, Vol.7, No.6, (Nov. 1996) 1491–1496CrossRefGoogle Scholar
  4. 4.
    Srinivasa V. Chakravarthy and Joydeep Ghosh, “A Neural Network-based Associative Memory for Storing Complex-valued Patterns”, Systems, Man, and Cybernetics, 1994, Intel. Conf., 2213–2218Google Scholar
  5. 5.
    Widrow, B., McCool, J., & Ball, M., “The complex LMS algorithm”, Proceedings of the IEEE, 63(4) (1975) 719–720Google Scholar
  6. 6.
    A. Hirose, “Proposal of fully complex-valued Neural Networks”, In Proceedings of the International Joint Conference on Neural Networks, Vol. 4 (1992) 152–157Google Scholar
  7. 7.
    Pan Yong, Li lei and Shi Hongbao, “An Integral Neural Network Based on Complex Domain”, Advances in Computer Science and Technology, Proceeding of the Fifth International Conference for Young Computer Scientists, Vol.1 (1999) 537–539Google Scholar
  8. 8.
    Pan Yong, Li lei and Shi Hongbao, “An Integral Neural Network Based on Complex Domain and its applications”, Proceeding of International Symposium on Domain Theory (1999)Google Scholar
  9. 9.
    Price, D et al, Pairwise Neural Network Classifiers with Probabilistic Outputs, NIPS (1996) 1009–1116Google Scholar
  10. 10.
    Ulbricht C, Dorffner G., Canu S., Guillemyn D., Marijuan G., Olarte J., Rodriguez C, Martin L, Mechanisms for Handling Sequences with Neural Networks, Intelligent Engineering Systems through Artificial Neural Networks, Volume 2, ASME Press, New York, 1992.Google Scholar
  11. 11.
    Ulbricht C, Handling Sequences with a Competitive Recurrent Network, Proceedings of the International Joint Conference on Neural Networks, Baltimore, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Pan Yong
    • 1
  • Shi Hongbao
    • 2
  • Li Lei
    • 2
  1. 1.Institute of Computing Technology, Tongji University(West Campus)Shanghai
  2. 2.Suzhou Railway Teachers CollegeJiangsu

Personalised recommendations