Multiscale BiLinear Recurrent Neural Network with an Adaptive Learning Algorithm

  • Byung-Jae Min
  • Chung Nguyen Tran
  • Dong-Chul Park
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)


In this paper, a wavelet-based neural network architecture called the Multiscale BiLinear Recurrent Neural Network with an adaptive learning algorithm (M-BLRNN(AL)) is proposed. The proposed M-BLRNN(AL) is formulated by a combination of several BiLinear Recurrent Neural Network (BLRNN) models in which each model is employed for predicting the signal at a certain level obtained by a wavelet transform. The learning process is further improved by applying an adaptive learning algorithm at each resolution level. The proposed M-BLRNN(AL) is applied to the long-term prediction of MPEG VBR video traffic data. Experiments and results on several MPEG data sets show that the proposed M-BLRNN(AL) outperforms the traditional MultiLayer Perceptron Type Neural Network (MLPNN), the BLRNN, and the original M-BLRNN in terms of the normalized mean square error (NMSE).


Recurrent Neural Network Resolution Level Adaptive Learning Asynchronous Transfer Mode Normalize Mean Square Error 
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.
    Nomura, N., Fujii, T., Ohta, N.: Basic Characteristics of Variable Rate Video Coding in ATM Environment. IEEE J. Select. Areas Commun. 7, 752–760 (1989)CrossRefGoogle Scholar
  2. 2.
    Adas, A.M.: Using Adaptive Linear Prediction to Support Real-time VBR Video under RCBR Network Service Model. IEEE/ACM Trans. Networking 6, 635–644 (1998)CrossRefGoogle Scholar
  3. 3.
    Bhattacharya, A., Parlos, A.G., Atiya, A.F.: Prediction of MPEG-coded Video Source Traffic using Recurrent Neural Networks. IEEE Trans. on Acoustics, Speech, and Signal Processing 51, 2177–2190 (2003)Google Scholar
  4. 4.
    Park, D.C., Zhu, Y.: Bilinear Recurrent Neural Network. IEEE ICNN 3, 1459–1464 (1994)Google Scholar
  5. 5.
    Mallat, S.G.: A Theory for Multiresolution Signal Decomposition: the Wavelet Representation. IEEE Trans. Pattern Anal. Machine Intell. 11, 674–693 (1989)MATHCrossRefGoogle Scholar
  6. 6.
    Shensa, M.J.: The Discrete Wavelet Transform: Wedding the À Trous and Mallat Algorithms. IEEE Trans. Signal Proc. 10, 2463–2482 (1992)Google Scholar
  7. 7.
    Liang, Y., Page, E.W.: Multiresolution Learning Paradigm and Signal Prediction. IEEE Trans. Sig. Proc. 45, 2858–2864 (1997)CrossRefGoogle Scholar
  8. 8.
    Park, D.C., Jeong, T.K.: Complex Bilinear Recurrent Neural Network for Equalization of a Satellite Channel. IEEE Trans on Neural Network 13, 711–725 (2002)CrossRefGoogle Scholar
  9. 9.
    Kruschke, J.K., Movellan, J.R.: Benefits of Gain: Speeded Learning and Minimal Hidden Layers in Back-propagation Networks. IEEE Trans. on Systems, Man and Cybernetics 21(1), 273–280 (1991)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Parlos, A.G., Rais, O.T., Atiya, A.F.: Multi-step-ahead Prediction using Dynamic Recurrent Neural Networks. In: IJCNN 1999. Int. Joint Conf. on Neural Networks, vol. 1, pp. 349–352 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Byung-Jae Min
    • 1
  • Chung Nguyen Tran
    • 1
  • Dong-Chul Park
    • 1
  1. 1.ICRL, Dept. of Information EngineeringMyong Ji UniversityKorea

Personalised recommendations