Advertisement

Journal of Electronics (China)

, Volume 11, Issue 1, pp 88–92 | Cite as

Analog circuit implementation of neural network with high precision weights

  • Gao Lina
  • Qiu Guanyuan
Research Notes
  • 35 Downloads

Abstract

A current-mode MOS neuron circuit with 4-bit programmable weights is presented by using CMOS technology. The weights of the neuron have high resolution and also can easily be digitally stored. The resolution can be extended into high levels such as 8-bit, etc. by the design methodology presented in this paper. The operational principle of the neuron is discussed. Circuit simulation has been made by use of SPICE II. The results give a good agreement for the design requirements.

Key words

Neural networks Neurons MOS integrated circuits 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    L. E. Atlas, Yoshitake Suzuke,IEEE Circuits and Devices Magazine,5 (1989) 6, 20–24.CrossRefGoogle Scholar
  2. [2]
    H. P. Graf, L. D. Jackel,IEEE Circuits and Devices Magazine,5 (1989) 4, 44–49.CrossRefGoogle Scholar
  3. [3]
    S. Y. Foo, L. R. Anderson, Yoshiyasu Takefuji,IEEE Circuits and Devices Magazine,6 (1990) 4, 18–26.CrossRefGoogle Scholar
  4. [4]
    M. Vereysen, P. G. A. Jespers,IEEE Micro,9 (1989) 6, 46–55.CrossRefGoogle Scholar
  5. [5]
    A. G. Andreou et al.,IEEE Trans. on NN,NN-2 (1991) 2, 205–213.Google Scholar
  6. [6]
    G. Moon, M. E. Zaghloul, R. W. Newcomb,IEEE Trans. on NN,NN-2 (1992) 3, 394–403.Google Scholar

Copyright information

© Science Press 1994

Authors and Affiliations

  • Gao Lina
    • 1
  • Qiu Guanyuan
    • 1
  1. 1.Xi'an Jiaotong UniversityXi'an

Personalised recommendations