VLSI Implementations of Neural Network Models

  • H. P. Graf
  • L. D. Jackel


Three experimental CMOS VLSI circuits implementing connectionist neural network models are discussed in this paper. These chips contain networks of highly interconnected simple processing elements that execute a task distributed over the whole network. A combination of analog and digital computation allows us to build compact circuits so that large networks can be packed on a single chip. Such networks are well-suited for pattern matching and classification tasks, operations that are hard to solve efficiently on a serial architecture.


Input Vector Neural Network Model Single Chip Inhibitory Connection Input Line 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    M.A. Sivilotti, M.R. Emerling, and C.A. Mead, VLSI Architectures for Implementation of Neural Networks Proc. Conf. Neural Networks for Computing, Snowbird, Utah, 1986, J.S. Denker ed., p.408, AIP Proc. 151.Google Scholar
  2. [2]
    H.P. Graf and P. deVegvar, A CMOS Implementation of a Neural Network Model, in Advanced Research in VLSI, Proc. Stanford Conf. 1987, P.Losleben ed., MIT Press, p. 351.Google Scholar
  3. [3]
    J.P. Sage, K. Thompson, and R.S. Withers, An Artificial Neural Network Integrated Circuit Based on MNOS/CCD Principles Proc. Conf. Neural Networks for Computing, Snowbird, Utah, 1986, J.S. Denker (ed.), p. 381, AIP Proc. 151.Google Scholar
  4. [4]
    J. Raffel, J. Mann, R. Berger, A. Soares, S. Gilbert, A Generic Architecture for Wafer-Scale Neuromorphic Systems, Proc. IEEE Int. Conf. Neural Networks, San Diego, 1987, p. III-501, M. Caudill and C. Butler (eds.), IEEE 87TH0191–7.Google Scholar
  5. [5]
    A. P. Thakoor, A. Moopen, J. Lambe and S. K. Khanna, Electronic Hardware Implementations of Neural Networks, Applied Optics, 26, p. 5085 (1987).CrossRefGoogle Scholar
  6. [6]
    D. W. Tank and J. J. Hopfield, Simple “Neural” Optimization Networks: An A/D Converter, Signal decision Circuit and a Linear Programming Circuit, IEEE Trans. Circuits and Systems, CAS-33, p. 533 (1986).Google Scholar
  7. [7]
    For an up-to-date picture of the status of neural network modeling see e.g.: Proc. IEEE Conf. Neural Information Processing Systems - Natural and Synthetic in Denver, Colorado,1987, D.Anderson (ed. ), American Institute of Physics (publisher ), (1988).Google Scholar
  8. [8]
    D.E. Rumelhart, J.L. McClelland, and the PDP Research Group, Parallel Distributed Processing, MIT Press, (1986).Google Scholar
  9. [9]
    T. Kohonen, Self-Organization and Associative Memory, Springer Verlag, New York, (1984).Google Scholar
  10. [10]
    G. Carpenter and S. Grossberg, ART 2: Self-Organization of Stable Category Recognition Code for Analog Input Patterns, Applied Optics, 26, p. 4919, (1987).CrossRefGoogle Scholar
  11. [11]
    R.P Lippmann, An Introduction to Computing with Neural Nets, IEEE ASSP Magazine, 4/2 p. 4, (1987).CrossRefGoogle Scholar
  12. [12]
    J.S. Denker, D. Schwartz, B. Wittner, S. Solla, R. Howard, L.Jackel and J. Hopfield, Large Automatic Learning, Rule Extraction, and Generalization, Complex Systems, 1, p. 877, (1987).Google Scholar
  13. [13]
    L.D. Jackel, R.E. Howard, H.P. Graf, B. Straughn, and J.S. Denker, Artificial Neural Networks for Computing, J. Vac. Sci. Tech., B4, p. 61 (1986).Google Scholar
  14. [14]
    H.P. Graf, L.D. Jackel, R.E. Howard, B. Straughn, J.S. Denker, W. Hubbard, D.M. Tennant, and D. Schwartz, VLSI Implementation of a Neural Network Memory with Several Hundred Neurons,Proc. Conf. Neural Networks for Computing, 1986, J.S. Denker (ed.), p.182, AIP Proc 151.Google Scholar
  15. [15]
    H.P. Graf, L.D. Jackel, and W. Hubbard, VLSI Implementation of a Neural Network Model, IEEE COMPUTER, March 1988.Google Scholar
  16. [16]
    M.J.M. Pelgrom, H.E.J. Wulms, P. Van Der Stokker, and R.A. Bergamaschi, FEBRIS: A Chip for Pattern Recognition, IEEE J. Solid-State Circuits, SC-22, p. 423, (1987).Google Scholar

Copyright information

© Plenum Press, New York 1988

Authors and Affiliations

  • H. P. Graf
    • 1
  • L. D. Jackel
    • 1
  1. 1.AT&T Bell LaboratoriesHolmdelUSA

Personalised recommendations