A Fully Complex-valued Radial Basis Function Network and Its Learning Algorithm

  • Sundaram Suresh
  • Narasimhan Sundararajan
  • Ramasamy Savitha
Part of the Studies in Computational Intelligence book series (SCI, volume 421)

Abstract

Radial basis function networks are the most popular neural network architecture due its simpler structure and better approximation ability owing to the localization property of the Gaussian function. in this chapter, we study complex-valued RBF networks and their learning algorithms. First, we present a complex-valued RBF network which is a direct extension of the real-valued RBF network. CRBF network is a single hidden layer networkwhich computes the output of the network as a linear combination of the hidden neuron outputs.

Keywords

Radial Basis Function Extreme Learning Machine Hide Neuron Radial Basis Function Neural Network Radial Basis Function Network 
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.

References

  1. 1.
    Savitha, R., Suresh, S., Sundararajan, N.: A fully complex-valued radial basis function network and its learning algorithm. International Journal of Neural Systems 19(4), 253–267 (2009)CrossRefGoogle Scholar
  2. 2.
    Nelson, T.O., Narens, L.: Metamemory: A theoritical framework and new findings. In: Nelson, T.O. (ed.) Metacognition: Core Readings, pp. 9–24. Allyn and Bacon, Boston (1980)Google Scholar
  3. 3.
    Chen, S., McLaughlin, S., Mulgrew, B.: Complex valued radial basis function network,part I: Network architecture and learning algorithms. EURASIP Signal Processing Journal 35(1), 19–31 (1994)CrossRefMATHGoogle Scholar
  4. 4.
    Chen, S., McLaughlin, S., Mulgrew, B.: Complex valued radial basis function network, part II: Application to digital communications channel equalization. Signal Processing 36(2), 175–188 (1994)CrossRefMATHGoogle Scholar
  5. 5.
    Cha, I., Kassam, S.A.: Channel equalization using adaptive complex radial basis function networks. IEEE Journal on Selected Areas in Communications 13(1), 122–131 (1995)CrossRefGoogle Scholar
  6. 6.
    Chen, S., Hong, X., Harris, C.J., Hanzo, L.: Fully complex-valued radial basis function networks: Orthogonal least squares regression and classification. Neurocomputing 71(16-18), 3421–3433 (2008)CrossRefGoogle Scholar
  7. 7.
    Li, M.B., Huang, G.-B., Saratchandran, P., Sundararajan, N.: Fully complex extreme learning machine. Neurocomputing 68(1-4), 306–314 (2005)CrossRefGoogle Scholar
  8. 8.
    Jianping, D., Sundararajan, N., Saratchandran, P.: Complex-valued minimal resource allocation network for nonlinear signal processing. International Journal of Neural Systems 10(2), 95–106 (2000)Google Scholar
  9. 9.
    Li, M.B., Huang, G.B., Saratchandran, P., Sundararajan, N.: Complex-valued growing and pruning RBF neural networks for communication channel equalisation. IEE Proceedings- Vision, Image and Signal Processing 153(4), 411–418 (2006)CrossRefGoogle Scholar
  10. 10.
    Yingwei, L., Sundararajan, N., Saratchandran, P.: A sequential learning scheme for function approximation using minimal radial basis function neural networks. Neural Computation 9(2), 461–478 (1997)CrossRefMATHGoogle Scholar
  11. 11.
    Yingwei, L., Sundararajan, N., Saratchandran, P.: Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm. IEEE Transactions on Neural Networks 9(2), 308–318 (1998)CrossRefGoogle Scholar
  12. 12.
    Huang, G.B., Saratchandran, P., Sundararajan, N.: An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks. IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics 34(6), 2284–2292 (2004)CrossRefGoogle Scholar
  13. 13.
    Suresh, S., Omkar, S.N., Mani, V., Prakash, T.N.G.: Lift coefficient prediction at high angle of attack using recurrent neural network. Aerospace Science and Technology 7(8), 595–602 (2003)CrossRefMATHGoogle Scholar
  14. 14.
    Kim, T., Adali, T.: Fully complex multi-layer perceptron network for nonlinear signal processing. Journal of VLSI Signal Processing 32(1/2), 29–43 (2002)MATHGoogle Scholar
  15. 15.
    Kim, T., Adali, T.: Approximation by fully complex multi-layer perceptrons. Neural Computation 15(7), 1641–1666 (2003)CrossRefMATHGoogle Scholar
  16. 16.
    Rollet, R., Benie, G.B., Li, W., Wang, S., Boucher, J.M.: Image classification algorithm based on the RBF neural network and K-means. International Journal of Remote Sensing 19(15), 3003–3009 (1998)CrossRefGoogle Scholar
  17. 17.
    Wenden, A.L.: Meta-cognitive knowledge and language learning. Applied Linguistics 19(4), 515–537 (1998)CrossRefGoogle Scholar
  18. 18.
    Rivers, W.P.: Autonomy at all costs: An ethnography of meta-cognitive self-assessment and self-management among experienced language learners. The Modern Language Journal 85(2), 279–290 (2001)CrossRefGoogle Scholar
  19. 19.
    Isaacson, R., Fujita, F.: Metacognitive knowledge monitoring and self-regulated learning: Academic success and reflections on learning. Journal of the Scholarship of Teaching and Learning 6(1), 39–55 (2006)Google Scholar
  20. 20.
    Josyula, D.P., Vadali, H., Donahue, B.J., Hughes, F.C.: Modeling metacognition for learning in artificial systems. In: Proceedings of 2009 World Congress on Nature and Biologically Inspired Computing (NABIC 2009), pp. 1419–1424 (2009)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2013

Authors and Affiliations

  • Sundaram Suresh
    • 1
  • Narasimhan Sundararajan
    • 2
  • Ramasamy Savitha
    • 1
  1. 1.School of Computer EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.School of Electrical and Electronics EngineeringNanyang Technological UniversitySingaporeSingapore

Personalised recommendations