Improvement of ANNs Performance to Generate Fitting Surfaces for Analog CMOS Circuits

  • José Ángel Díaz-Madrid
  • Pedro Monsalve-Campillo
  • Juan Hinojosa
  • María Victoria Rodellar Biarge
  • Ginés Doménech-Asensi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4528)


One of the typical applications of neural networks is based on their ability to generate fitting surfaces. However, for certain problems, error specifications are very restrictive, and so, the performance of these networks must be improved. This is the case of analog CMOS circuits, where models created must provide an accuracy which some times is difficult to achieve using classical techniques. In this paper we describe a modelling method for such circuits based on the combination of classical neural networks and electromagnetic techniques. This method improves the precision of the fitting surface generated by the neural network and keeps the training time within acceptable limits.


ANNs Performance Coarse Model Classical Neural Network Fitting Surface CMOS Circuit 
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.
    Boyle, G.R., Cohn, B.M., Pederson, D.O., Solomon, J.E.: Macromodeling of Operational Integrated Circuit Amplifiers. IEEE Journal of Solid–State Circuits 9, 353–364 (1974)CrossRefGoogle Scholar
  2. 2.
    Wei, Y., Doboli, A.: Library of structural cell macromodels for design of continuous-time reconfigurable Delta-Sigma modulators. In: IEEE Intl. Symp. on Circuits and Systems, pp. 1764–1767 (2006)Google Scholar
  3. 3.
    Doménech-Asensi, G., Hinojosa, J., Martínez-Alajarín, J., Garrigós-Guerrero, J.: Empirical Model Generation Techniques for Planar Microwave Components using Electromagnetic Linear Regression Models. IEEE Trans. Microwave Theory and Tech. 53, 3305–3311 (2005)CrossRefGoogle Scholar
  4. 4.
    Vancorenland, P., der Plas, G.V., Steyaert, M., Gielen, G., Sansen, W.: A Layout–aware Synthesis Methodology for RF Circuits. In: Proc. IEEE/ACM International Conference on Computer Aided Design, pp. 358–362 (2001)Google Scholar
  5. 5.
    McConaghy, T., Gielen, G.: Analysis of Simulation-Driven Numerical Performance Modeling Techniques for Application to Analog Circuit Optimization. In: IEEE Intl. Symp. on Circuits and Systems, pp. 1298–1301 (2005)Google Scholar
  6. 6.
    Watson, P.M., Gupta, K.C.: EM-ANN models for microstrip vias and interconnects in multilayer circuits. IEEE Trans. Microwave Theory Tech. 44, 2495–2503 (1996)CrossRefGoogle Scholar
  7. 7.
    Watson, P.M., Gupta, K.C., Mahajan, R.L.: Development of knowledge based artificial neural network models for microwave components. In: IEEE Int. Microwave Symp. Digest, pp. 9–12 (1998)Google Scholar
  8. 8.
    Bult, K., Geelen, G.J.G.M.: A Fast-Settling CMOS Op Amp for SC Circuits with 90-dB DC Gain. IEEE Journal of Solid-State Circuits 25, 1379–1384 (1998)CrossRefGoogle Scholar
  9. 9.
    Rumelhart, D.E., Inton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Data Processing, 1, pp. 318–362. MIT Press, Cambridge (1986)Google Scholar
  10. 10.
    Hagan, M.T., Menhaj, M.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. On Neural Networks 5, 989–993 (1994)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • José Ángel Díaz-Madrid
    • 1
  • Pedro Monsalve-Campillo
    • 2
  • Juan Hinojosa
    • 2
  • María Victoria Rodellar Biarge
    • 3
  • Ginés Doménech-Asensi
    • 2
  1. 1.Fraunhofer Institute, Erlangen 91058Germany
  2. 2.Universidad Politécnica de Cartagena, Cartagena 30202Spain
  3. 3.Universidad Politécnica de Madrid, Campus de Montegancedo, Madrid 28660Spain

Personalised recommendations