Advertisement

Application of Neural Networks for Integrated Circuit Modeling

  • Xi Chen
  • Gao-Feng Wang
  • Wei Zhou
  • Qing-Lin Zhang
  • Jiang-Feng Xu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)

Abstract

Application of feedforward neural networks for integrated circuit (IC) modeling is presented. In order to accurately describe IC behaviors, a set of improved equations for dynamic feedforward neural networks has been utilized for IC modeling. The rationality of the improved equations is elucidated by analyzing the relation between the circuits and the equation parameters. Through some special choices of the neuron nonlinearity function, the feed- forward neural networks can themselves be represented by equivalent circuits, which enables the direct use of neural models in existing analogue circuit simulators. Feedforward neural network models for some static and dynamic systems are obtained and compared. Simulated results are included to illustrate the accuracy of the neural networks in circuit modeling.

Keywords

Neural Network Feedforward Neural Network Modeling Task Circuit Simulation Dynamic Neural 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.
    Meijer, P.B.L.: Table Models for Device Modelling. In: Proc. Int. Symp. On Circuits and Syst., pp. 2593–2596 (1988)Google Scholar
  2. 2.
    Meijer, P.B.L.: Fast and Smooth Highly Nonlinear Table Models for Device Modeling. IEEE Trans. Circuits Syst. 37, 335–346 (1990)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer Feedforward Networks. Neural Networks 2, 359–366 (1989)CrossRefGoogle Scholar
  4. 4.
    Meijer, P.B.L.: Neural Network Applications in Device and Subcircuit Modelling for Circuit Simulation. Ph.D. Dissertation, Proefschrift Technische Universiteit, Eindhoven (2003)Google Scholar
  5. 5.
    Kim, T., Adali, T.: Universal Approximation of Fully Complex Feedforward Neural Networks. IEEE International Conference on Acoustics, Speech, and Signal Processing, 973–976 (2002)Google Scholar
  6. 6.
    Stinchcombe, M., White, H.: Universal Approximation Using Feedforward Networks with Non-sigmoid Hidden Layer Activation Functions. International Joint Conference on Neural Network, 613–617 (1989)Google Scholar
  7. 7.
    Xu, J.J., Yagoub, M.C.E., Ding, R.T., Zhang, Q.J.: Feedforward Dynamic Neural Network Technique for Modeling and Design of Nonlinear Telecommunication Circuits and Systems. In: Proceedings of the International Joint Conference on Neural Networks, pp. 930–935 (2003)Google Scholar
  8. 8.
    Ong, E., Flitman, A.: Using Neural Networks to Predict Binary Outcomes. Intelligent Processing Systems, 427–431 (1997)Google Scholar
  9. 9.
    Charalambous, C., Charitou, A., Kaourou, F.: Comparative Analysis of Artificial Neural Network Models: Application in Bankruptcy Prediction. International Joint Conference on Neural Networks, 3888–3893 (1999)Google Scholar
  10. 10.
    Suran, J.J.: Low–frequency Circuit Theory of the Double–base Diode. IEEE Transactions on Electron Devices 2, 44–48 (1955)CrossRefGoogle Scholar
  11. 11.
    Phillippe, P., El-Kamali, W., Pauker, V.: Physical Equivalent Circuit Model for Planar Schottky Varactor Diode. IEEE Transactions onMicrowave Theory and Techniques 36, 250–255 (1988)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xi Chen
    • 1
    • 2
  • Gao-Feng Wang
    • 1
    • 2
  • Wei Zhou
    • 1
    • 2
  • Qing-Lin Zhang
    • 1
    • 2
  • Jiang-Feng Xu
    • 3
  1. 1.School of Electronic InformationWuhan UniversityChina
  2. 2.Institute of Microelectronics and Information TechnologyWuhan UniversityChina
  3. 3.Shanghai Institute of Technical PhysicsChinese Academy of SciencesChina

Personalised recommendations