High Dimensional Neural Networks and Applications

  • B. K. Tripathi
  • P. K. Kalra
Part of the Studies in Computational Intelligence book series (SCI, volume 275)


Intelligent systems are emerging computing systems developed based on intelligent techniques. These techniques take advantage of artificial neural networks to emulate intelligent behavior. Extensive studies carried out during the past several years have revealed that neural networks enjoy numerous practical advantages over conventional methods. They are more fault-tolerant, less sensitive to noise and mostly used for their human-like characteristics (learning and generalization). They have been accepted as powerful tools for correlating data without making strong assumptions about the problems. Traditional neural networks’s parameters are usually real numbers for dealing with real-valued data. However, high-dimensional data also appear in practical applications and consequently, high-dimensional neural networks have been proposed. They have also presented improved results even in case of real-valued problems. As a prelude, we provide a brief overview of the existing methodologies in high-dimensional neural computation. Our particular point of view is to describe several real-world applications, in which the use of these techniques really helps in achieving the goals of intelligent system.


Neural Network Face Recognition Independent Component Analysis Face Image Hide Neuron 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McCulloch, W.S., Pitts, W.: A logical calculation of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Giles, C.L., Maxwell, T.: Learning, invariance and generalization in a high-order neural network. Applied Optics 26(23), 4972–4978 (1987)CrossRefGoogle Scholar
  3. 3.
    Cha, H.: Channel equalization using adaptive complex radial basis function networks. IEEE J. Select. Areas Communication 9, 122–131 (1995)Google Scholar
  4. 4.
    Jianping, D., Sundararajan, N., Saratchandran, P.: Communication channel equalization using complex-valued minimal radial basis function neural networks. IEEE Trans. on Neural Networks 13(3), 687–696 (2002)CrossRefGoogle Scholar
  5. 5.
    Igel, C., Husken, M.: Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing 50, 105–123 (2003)zbMATHCrossRefGoogle Scholar
  6. 6.
    Watanabe, A., Miyauchi, A., Miyauchi, M.: A method to interpret 3D motion using neural networks. IEICE Trans. on Fundamentals of Electronics and Computer Science E77-A(8), 1363–1370 (1994)Google Scholar
  7. 7.
    Nitta, T.: A 3D vector version of the back-propagation algorithm. In: Proc. of IJCNN 1992, Beijing, vol. 2, pp. 511–516 (1992)Google Scholar
  8. 8.
    Aizenberg, N.N., Ivaskiv, Y.L., Pospelov, D.A.: About one generalization of the threshold function. Doklady Akademii Nauk SSSR (The Reports of the Academy of Sciences of the USSR) 196(6), 1287–1290 (1971) (in Russian)MathSciNetGoogle Scholar
  9. 9.
    Aizenberg, I., Moraga, C.: Multilayer feed-forward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm. Soft Computing 11(2), 169–183 (2007)CrossRefGoogle Scholar
  10. 10.
    Aizenberg, I., Aizenberg, N., Vandewalle, J.: Multi-valued and universal binary neurons: theory, learning, applications. Kluwer Academic Publishers, Dordrecht (2000)Google Scholar
  11. 11.
    Kim, T., Adali, T.: Approximation by fully complex multilayer perceptrons. Neural Computation 15, 1641–1666 (2003)zbMATHCrossRefGoogle Scholar
  12. 12.
    Piazza, F., Benvenuto, N.: On the complex back-propagation algorithm. IEEE Transaction on Signal Processing 40(4), 967–969 (1992)CrossRefGoogle Scholar
  13. 13.
    Goh, S.L.: A complex-valued RTRL algorithm for recurrent neural networks. Neural Computation 16, 2699–2713 (2003)CrossRefGoogle Scholar
  14. 14.
    Leung, H., Haykin, S.: The complex back-propagation algorithm. IEEE Transaction on Signal Processing 39(9), 2101–2104 (1991)CrossRefGoogle Scholar
  15. 15.
    Nitta, T.: An extension of the back-propagation to complex numbers. Neural Networks 10(8), 1391–1415 (1997)CrossRefGoogle Scholar
  16. 16.
    Nitta, T.: Orthogonality of decision boundaries in complex-valued neural networks. Neural Computation 16(1), 73–97 (2004)zbMATHCrossRefGoogle Scholar
  17. 17.
    Nitta, T.: Solving the XOR problem and the detection of symmetry using a single complex-valued neuron. Neural Networks 16, 1101–1105 (2003)CrossRefGoogle Scholar
  18. 18.
    Jacobs, R.A.: Increased rates of convergence through learning rate adaptation. Neural Networks 1(4), 295–307 (1988)CrossRefGoogle Scholar
  19. 19.
    Nitta, T.: An analysis of the fundamental structure of complex-valued neurons. Neural Processing Letters 12, 239–246 (2000)zbMATHCrossRefGoogle Scholar
  20. 20.
    Brown, J.W., Churchill, R.V.: Complex Variables and Applications, 7th edn. McGraw-Hill, New York (2003)Google Scholar
  21. 21.
    Nitta, T.: Three-dimensional vector valued neural network and its generalization abilIty. Neural Information Processing – Letters and Reviews 10(10), 237–242 (2006)Google Scholar
  22. 22.
    Tripathi, B.K., Chandra, B., Kalra, P.K.: The generalized product neuron model in complex domain. In: Proc. of International Conference on Neural Information Processing, Auckland, New Zealand (2008)Google Scholar
  23. 23.
    Turk, M., Pentaland, A.P.: Face recognition using eigenfaces. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
  24. 24.
    Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: Face recognition by independent component analysis. IEEE Transaction on Neural Networks 3(6), 1450–1464 (2002)CrossRefGoogle Scholar
  25. 25.
    Rattan, S., Hsieh, W., Ruessink, B.G.: Nonlinear complex principal component analysis and its applications. In: Proceedings of International Joint Conference on Neural Networks, Montreal, Canada (2005)Google Scholar
  26. 26.
    Calhoun, V., Adali, T.: Complex ICA for FMRI analysis: performance of several approaches. In: Proc. of ICASSP (2003)Google Scholar
  27. 27.
    Kalra, P.K., Yadav, R.N., John, J.: Time series prediction with single multiplicative neuron model. Applied Soft Computing 7, 1157–1163 (2007)CrossRefGoogle Scholar
  28. 28.
    Gorman, R.P., Sejnowski, T.J.: Analysis of hidden units in a layered network trained to classify sonar targets. Neural Networks 1, 75–89 (1988)CrossRefGoogle Scholar
  29. 29.
    Tripathi, B.K., Kalra, P.K.: A complex valued heterogeneous neural network. In: Proc. of a Workshop on Complex Valued Neural Network, International Joint Conference on Artificial Intelligence, Hyderabad, India (2007)Google Scholar
  30. 30.
    Van Ooyen, A., Nienhuis, B.: Improving the convergence of the back-propagation algorithm. Neural Networks 5(3), 465–472 (1992)CrossRefGoogle Scholar
  31. 31.
    Chen, X., Tang, Z., Vairappan, C., Li, S., Okada, T.: A modified error back-propagation algorithm for complex-value neural networks. International Journal of Neural System 15(6), 435–443 (2005)CrossRefGoogle Scholar
  32. 32.
  33. 33.
    Blake, C.L., Merz, C.J.: UCI Repository of machine learning database. University of California, Department of Information and computer science (1998),
  34. 34.
  35. 35.
    Gupta, M.M., Homma, N.: Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory. Wiley, Chichester (2003)CrossRefGoogle Scholar
  36. 36.
    Hirose, A.: Complex-Valued Neural Networks. Springer, New York (2006)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • B. K. Tripathi
    • 1
  • P. K. Kalra
    • 2
  1. 1.107-ACES, Indian Institute of TechnologyKanpurIndia
  2. 2.Indian Institute of TechnologyRajasthanIndia

Personalised recommendations