Abstract

This paper reviews two custom electronic circuits that implement some simple models of neural function. The circuits include a thin-film array of read-only resistive synapses and an array of programmable synapses and amplifiers serving as electronic neurons. Circuit performance and architecture are discussed.

© 1987 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. For a sampling of current research in neural modeling and artificial neural nets see J. S. Denker, Ed., Neural Networks For Computing, AIP Conf. Proc. 151 (1986).
  2. D. O. Hebb, The Organization of Behavior (Wiley, New York, 1949).
  3. W. Hubbard et al., “Electronic Neural Networks,” AIP Conf. Proc. 151, 227 (1986).
    [CrossRef]
  4. D. B. Schwartz et al., “Dynamics of Microfabricated Electronic Neural Networks,” Appl. Phys. Lett. 50, 1110 (1987).
    [CrossRef]
  5. J. S. Denker, “Neural Network Models of Learning and Adaptation,” Physica D, vol 22, (1986) p. 216.
    [CrossRef]
  6. H. P. Graf, P. deVegvar, “A CMOS Associative Memory Chip Based on Neural Networks,” in Technical Digest International Solid-State Circuits Conference IEEE, (New York, 1987), p. 304.
  7. H. P. Graf, P. deVegvar, “A CMOS Implementation of a Neural Network Model,” in Proceedings, Stanford Conference on Advanced Research in VLSI, March 1987 (MIT Press, Cambridge, 1987), p. 351.
  8. J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.
  9. J. J. Hopfield, D. W. Tank, “‘Neural’ Computation of Decisions in Optimization Problems,” Biol. Cybern. 52, 141 (1985).
    [PubMed]

1987 (1)

D. B. Schwartz et al., “Dynamics of Microfabricated Electronic Neural Networks,” Appl. Phys. Lett. 50, 1110 (1987).
[CrossRef]

1986 (3)

J. S. Denker, “Neural Network Models of Learning and Adaptation,” Physica D, vol 22, (1986) p. 216.
[CrossRef]

For a sampling of current research in neural modeling and artificial neural nets see J. S. Denker, Ed., Neural Networks For Computing, AIP Conf. Proc. 151 (1986).

W. Hubbard et al., “Electronic Neural Networks,” AIP Conf. Proc. 151, 227 (1986).
[CrossRef]

1985 (1)

J. J. Hopfield, D. W. Tank, “‘Neural’ Computation of Decisions in Optimization Problems,” Biol. Cybern. 52, 141 (1985).
[PubMed]

Denker, J. S.

J. S. Denker, “Neural Network Models of Learning and Adaptation,” Physica D, vol 22, (1986) p. 216.
[CrossRef]

J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.

deVegvar, P.

H. P. Graf, P. deVegvar, “A CMOS Associative Memory Chip Based on Neural Networks,” in Technical Digest International Solid-State Circuits Conference IEEE, (New York, 1987), p. 304.

H. P. Graf, P. deVegvar, “A CMOS Implementation of a Neural Network Model,” in Proceedings, Stanford Conference on Advanced Research in VLSI, March 1987 (MIT Press, Cambridge, 1987), p. 351.

Graf, H. P.

H. P. Graf, P. deVegvar, “A CMOS Implementation of a Neural Network Model,” in Proceedings, Stanford Conference on Advanced Research in VLSI, March 1987 (MIT Press, Cambridge, 1987), p. 351.

H. P. Graf, P. deVegvar, “A CMOS Associative Memory Chip Based on Neural Networks,” in Technical Digest International Solid-State Circuits Conference IEEE, (New York, 1987), p. 304.

Hebb, D. O.

D. O. Hebb, The Organization of Behavior (Wiley, New York, 1949).

Hopfield, J. J.

J. J. Hopfield, D. W. Tank, “‘Neural’ Computation of Decisions in Optimization Problems,” Biol. Cybern. 52, 141 (1985).
[PubMed]

Hubbard, W.

W. Hubbard et al., “Electronic Neural Networks,” AIP Conf. Proc. 151, 227 (1986).
[CrossRef]

Mackey, S.

J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.

Schwartz, D.

J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.

Schwartz, D. B.

D. B. Schwartz et al., “Dynamics of Microfabricated Electronic Neural Networks,” Appl. Phys. Lett. 50, 1110 (1987).
[CrossRef]

Tank, D. W.

J. J. Hopfield, D. W. Tank, “‘Neural’ Computation of Decisions in Optimization Problems,” Biol. Cybern. 52, 141 (1985).
[PubMed]

Wittner, B.

J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.

AIP Conf. Proc. (1)

W. Hubbard et al., “Electronic Neural Networks,” AIP Conf. Proc. 151, 227 (1986).
[CrossRef]

Appl. Phys. Lett. (1)

D. B. Schwartz et al., “Dynamics of Microfabricated Electronic Neural Networks,” Appl. Phys. Lett. 50, 1110 (1987).
[CrossRef]

Biol. Cybern. (1)

J. J. Hopfield, D. W. Tank, “‘Neural’ Computation of Decisions in Optimization Problems,” Biol. Cybern. 52, 141 (1985).
[PubMed]

Neural Networks For Computing (1)

For a sampling of current research in neural modeling and artificial neural nets see J. S. Denker, Ed., Neural Networks For Computing, AIP Conf. Proc. 151 (1986).

Physica D (1)

J. S. Denker, “Neural Network Models of Learning and Adaptation,” Physica D, vol 22, (1986) p. 216.
[CrossRef]

Other (4)

H. P. Graf, P. deVegvar, “A CMOS Associative Memory Chip Based on Neural Networks,” in Technical Digest International Solid-State Circuits Conference IEEE, (New York, 1987), p. 304.

H. P. Graf, P. deVegvar, “A CMOS Implementation of a Neural Network Model,” in Proceedings, Stanford Conference on Advanced Research in VLSI, March 1987 (MIT Press, Cambridge, 1987), p. 351.

J. S. Denker, S. Mackey, D. Schwartz, B. Wittner, AT&T Bell Laboratories; private communication.

D. O. Hebb, The Organization of Behavior (Wiley, New York, 1949).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (5)

Fig. 1
Fig. 1

Electronic neuron model.

Fig. 2
Fig. 2

Scanning electron micrograph of part of a 22 × 22 thin-film resistive synapse array.

Fig. 3
Fig. 3

Micrograph of fifty-four neuron chips with programmable synapses.

Fig. 4
Fig. 4

Programmable synapse functional diagram.

Fig. 5
Fig. 5

Grandmother cell architecture for associative recall.

Equations (1)

Equations on this page are rendered with MathJax. Learn more.

ν i = f ( j ν j T i j ) .

Metrics