Neurocomputing in Complex Domain

Part of the Studies in Computational Intelligence book series (SCI, volume 571)


There are many areas of applications which involve signals that are inherently complex-valued. The characteristics of these applications can be effectively realized if they are operated with the complex-valued neural networks (CVNNs). Apart from that it is also widely observed in researches that the real-valued problems can be solved far efficiently if they are represented and operated in the complex domain. Therefore, CVNNs have emerged a very good alternative in second generation of neurocomputing. The CVNNs to preserve and process the data (signals) in the complex domain itself are gaining more attention over their real-valued counterparts. The use of neural networks is naturally accompanied by the trade-off between issues such as the overfitting, generalization capability, local minima problems, and stability of the weight-update system. The main obstacle in the development of a complex-valued neural network (CVNN) and its learning algorithm is the selection of an appropriate activation function and error function (EF). It can be said that the suitable error function-based training scheme with a proper choice of activation function can substantially decrease the epochs and improve the generalization ability for the problem in question. This chapter presents prominent functions as a basis for making these choices and designing a learning scheme. The choice of EF and activation function in the training scheme also circumvents some of the existing lacunae such as error getting stuck and not progressing below a certain value. This chapter further introduces a novel approach to improve resilient propagation in complex domain for fast learning.


Activation Function Error Function Complex Domain Real Domain Absolute Function 


  1. 1.
    Hirose, A.: Complex-Valued Neural Networks. Springer, New York (2006)CrossRefMATHGoogle Scholar
  2. 2.
    Nitta, T.: Orthogonality of decision boundaries in complex-valued neural networks. Neural Comput. 16(1), 73–97 (2004)CrossRefMATHGoogle Scholar
  3. 3.
    Aizenberg, I., Moraga, C.: Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a back-propagation learning algorithm. Soft Comput. 11(2), 169–183 (2007)Google Scholar
  4. 4.
    Amin, M.F., Murase, K.: Single-layered complex-valued neural network for real-valued classification problems. Neurocomputing 72(4–6), 945–955 (2009)CrossRefGoogle Scholar
  5. 5.
    Savitha, R., Suresh, S., Sundararajan, N., Kim, H.J.: Fast learning fully complex-valued classifiers for real-valued classification problems. In: Liu, D., et al. (eds.) ISNN 2011, Part I, Lecture Notes in Computer Science (LNCS), vol. 6675, pp. 602–609 (2011)Google Scholar
  6. 6.
    Savitha, R., Suresh, S., Sundararajan, N., Kim, H.J.: A fully complex-valued radial basis function classifier for real-valued classification. Neurocomputing 78(1), 104–110 (2012)Google Scholar
  7. 7.
    Nitta, T.: An extension of the back-propagation algorithm to complex numbers. Neural Netw. 10(8), 1391–1415 (1997)CrossRefGoogle Scholar
  8. 8.
    Tripathi, B.K., Kalra, P.K.: Complex generalized-mean neuron model and its applications. Appl. Soft Comput. (Elsevier Science) 11(1), 768–777 (2011)Google Scholar
  9. 9.
    Nitta, T.: An analysis of the fundamental structure of complex-valued neurons. Neural Process. Lett. 12, 239–246 (2000)CrossRefMATHGoogle Scholar
  10. 10.
    Savitha, R., Suresh, S., Sundararajan, N., Saratchandran, P.: A new learning algorithm with logarithmic performance index for complex- valued neural networks. Neurocomputing 72(16–18), 3771–3781 (2009)CrossRefGoogle Scholar
  11. 11.
    Kim, T., Adali, T.: Approximation by fully complex multilayer perceptrons. Neural Comput. 15, 1641–1666 (2003)CrossRefMATHGoogle Scholar
  12. 12.
    Savitha, R., Suresh, S., Sundararajan, N.: A fully complex-valued radial basis function network and its learning algorithm. Int. J. Neural Syst. 19(4), 253–267 (2009)CrossRefGoogle Scholar
  13. 13.
    Amin, M.F., Islam, M.M., Murase, K.: Ensemble of single-layered complex-valued neural networks for classification tasks. Neurocomputing 72(10–12), 2227–2234 (2009)CrossRefGoogle Scholar
  14. 14.
    Li, M.-B., Huang, G.-B., Saratchandran, P., Sundararajan, N.: Fully complex extreme learning machine. Neurocomputing 68, 306–314 (2005)Google Scholar
  15. 15.
    Brown, J.W., Churchill, R.V.: Complex Variables and Applications, \({\rm {VII}}\)th edn. Mc Graw Hill, New York (2003)Google Scholar
  16. 16.
    Saff, E.B., Snider, A.D.: Fundamentals of Complex Analysis with Applications to Engineering and Science. Prentice Hall, Englewood Cliffs (2003)Google Scholar
  17. 17.
    Piazza, F., Benvenuto, N.: On the complex backpropagation algorithm. IEEE Trans. Sig. Proc. 40(4), 967–969 (1992)Google Scholar
  18. 18.
    Tripathi, B.K., Kalra, P.K.: The novel aggregation function based neuron models in complex domain. Soft Comput. (Springer) 14(10), 1069–1081 (2010)Google Scholar
  19. 19.
    Georgiou, G.M., Koutsougeras, C.: Complex domain backpropagation. IEEE Trans. Circuits Systems-II: Analog Digital Signal Proc. 39(5), 330–334 (1992)Google Scholar
  20. 20.
    Widrow, B., McCool, J., Ball, M.: The complex LMS algorithm. Proc. IEEE 63(4), 719–720 (1975)CrossRefGoogle Scholar
  21. 21.
    Leung, H., Haykin, S.: The complex backpropagation algorithm. IEEE Trans. Signal Proc. 39(9) (1991)Google Scholar
  22. 22.
    Tripathi, B.K., Kalra, P.K.: Functional mapping with complex higher order compensatory neuron model. In: World Congress on Computational Intelligence (WCCI-2010). ISSN: 1098–7576. IEEE Xplore, Barcelona, Spain, 18–23 July 2010Google Scholar
  23. 23.
    Kim, M.S., Guest, C.C.: Modification of backpropagation networks for complex-valued signal processing in frequency domain. In: Proceedings of IJCNN, San Diego (1990)Google Scholar
  24. 24.
    Tripathi, B.K., Kalra, P.K.: On efficient learning machine with root power mean neuron in complex domain. IEEE Trans. Neural Netw. 22(05), 727–738, ISSN: 1045–9227 (2011)Google Scholar
  25. 25.
    Mandic, D., Goh, V.S.L.: Complex valued nonlinear adaptive filters: noncircularity, widely linear and neural models. Wiley, Hoboken (2009)CrossRefGoogle Scholar
  26. 26.
    Shin, Y., Jin, K.-S., Yoon, B.-M.: A complex pi-sigma network and its application to equalization of nonlinear satellite channels. In: IEEE International Conference on Neural Networks (1997)Google Scholar
  27. 27.
    Igel, C., Husken, M.: Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing 50, 105–123 (2003)Google Scholar
  28. 28.
    Van Ooyen, A., Nienhuis, B.: Improving the convergence of the back-propagation algorithm. Neural Netw. 5(3), 465–472 (1992)CrossRefGoogle Scholar
  29. 29.
    Chen, L., Zhang, L., Zhang, H., Abdel-Mottaleb, M.: 3D Shape constraint for facial feature localization using probabilistic-like output. In: Proceeding of 6th IEEE International Conference on Automatic Face and Gesture Recognition (2004)Google Scholar
  30. 30.
    Jacobs, R.A.: Increased rates of convergence through learning rate adaptation. Neural Netw. 1(4), 295–307 (1988)CrossRefGoogle Scholar
  31. 31.
    Fahlman, S.E.: An empirical study of learning speed in back-propagation networks. In: Technical report, CMU-CS-88-162 (1988)Google Scholar
  32. 32.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster back-propagation learning: the RPROP algorithm. In: Proceeding of IEEE ICNN’93, San Francisco, pp. 586–591 (1993)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Computer Science and EngineeringHarcourt Butler Technological InstituteKanpurIndia

Personalised recommendations