Effects of Analog-VLSI Hardware on the Performance of the LMS Algorithm

  • Gonzalo Carvajal
  • Miguel Figueroa
  • Seth Bridges
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)


Device mismatch, charge leakage and nonlinear transfer functions limit the resolution of analog-VLSI arithmetic circuits and degrade the performance of neural networks and adaptive filters built with this technology. We present an analysis of the impact of these issues on the convergence time and residual error of a linear perceptron using the Least-Mean-Square (LMS) algorithm. We also identify design tradeoffs and derive guidelines to optimize system performance while minimizing circuit die area and power dissipation.


Mean Square Error Learning Rate Minimal Mean Square Error Convergence Time Forward Path 
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.
    Card, H.C., Dolenko, B.K., McNeill, D.K., Schneider, C.R., Schneider, R.S.: Is VLSI Neural Learning Robust Against Circuit Limitations? In: IEEE International Conference on Neural Networks, Miami, FL, USA, vol. 3, pp. 1889–1893 (1994)Google Scholar
  2. 2.
    Dolenko, B., Card, H.: Tolerance to Analog Hardware of On-Chip Learning in Backpropagation Networks. IEEE Transactions on Neural Networks 6(5), 1045–1052 (1995)CrossRefGoogle Scholar
  3. 3.
    Figueroa, M., Matamala, E., Carvajal, G., Bridges, S.: Adaptive Signal Processing in Mixed-Signal VLSI with Anti-Hebbian Learning. In: IEEE Computer Society Annual Symposium on VLSI, Karlsruhe, Germany, pp. 133–138. IEEE, Los Alamitos (2006)Google Scholar
  4. 4.
    Flores, A., Widrow, B.: Assessment of the Efficiency of the LMS algorithm Based on Spectral Information. In: Asilomar Conf. on Signals, Systems and Computers, Pacific Grove, CA, vol. 1, pp. 120–124 (2004)Google Scholar
  5. 5.
    McNeill, D.K., Card, H.C.: Analog Hardware Tolerance of Soft Competitive Learning. In: IEEE International Conference on Neural Networks, Miami, FL, USA, vol. 4, pp. 2004–2008 (1994)Google Scholar
  6. 6.
    Mead, C.: Analog VLSI and Neural Systems. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  7. 7.
    Pelgrom, M.J.M., Duinmaijer, A.C.J., Welbers, A.P.G.: Matching Properties of MOS Transistors. IEEE Journal of Solid-State Circuits 24(5), 1433–1440 (1989)CrossRefGoogle Scholar
  8. 8.
    Widrow, B., Walach, E.: Adaptive Inverse Control. Prentice-Hall, Upper Saddle River (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gonzalo Carvajal
    • 1
  • Miguel Figueroa
    • 1
  • Seth Bridges
    • 2
  1. 1.Department of Electrical EngineeringUniversidad de ConcepciónChile
  2. 2.Computer Science and EngineeringUniversity of WashingtonUSA

Personalised recommendations