Abstract

An optical neural network using two tightly cascaded liquid crystal televisions is presented. This new optical architecture offers compactness in size, ease of alignment, higher light efficiency, better image quality, and low cost. The implementation of the autoassociative and heteroassociative memories is given.

© 1990 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. N. H. Farhat, D. Psaltis, A. Prata, E. G. Paek, “Optical Implementation of the Hopfield Model,” Appl. Opt. 24, 1469–1475 (1985).
    [CrossRef] [PubMed]
  2. N. H. Farhat, D. Psaltis, “Optical Implementation of Associative Memory Based on Models of Neural Networks,” in Optical Signal Processing, J. L. Horner, Ed. (Academic, New York, 1987), pp. 129–162.
  3. B. Macukow, H. H. Arsenault, “Optical Associative Memory Model Based on Neural Networks Having Variable Interconnection Weights,” Appl. Opt. 26, 924–928 (1987).
    [CrossRef] [PubMed]
  4. J.-S. Jang, S.-W. Jung, S.-Y. Lee, S.-Y. Shin, “Optical Implementation of the Hopfield Model for Two-Dimensional Associative Memory,” Opt. Lett. 13, 248–250, (1988).
    [CrossRef] [PubMed]
  5. S. Wu, T. Lu, X. Xu, F. T. S. Yu, “An Adaptive Optical Neural Network Using a High Resolution Video Monitor,” Microwave Opt. Technol. Lett. 2, 252–257 (1989).
    [CrossRef]
  6. T. Lu, S. Wu, X. Xu, F. T. S. Yu, “Two-Dimensional Programmable Optical Neural Network,” Appl. Opt. 28, 4908–4913 (1989).
    [CrossRef] [PubMed]
  7. F. T. S. Yu, T. Lu, X. Yang, “Optical Neural Network Using Pocket Size Liquid Crystal Televisions,” Opt. Lett. 15, 863–865 (1990).
    [CrossRef] [PubMed]
  8. T. Lu, X. Xu, S. Wu, F. T. S. Yu, “Neural Network Model Using Interpattern Association,” Appl. Opt. 29, 284–288 (1990).
    [CrossRef] [PubMed]

1990 (2)

1989 (2)

T. Lu, S. Wu, X. Xu, F. T. S. Yu, “Two-Dimensional Programmable Optical Neural Network,” Appl. Opt. 28, 4908–4913 (1989).
[CrossRef] [PubMed]

S. Wu, T. Lu, X. Xu, F. T. S. Yu, “An Adaptive Optical Neural Network Using a High Resolution Video Monitor,” Microwave Opt. Technol. Lett. 2, 252–257 (1989).
[CrossRef]

1988 (1)

1987 (1)

1985 (1)

Arsenault, H. H.

Farhat, N. H.

N. H. Farhat, D. Psaltis, A. Prata, E. G. Paek, “Optical Implementation of the Hopfield Model,” Appl. Opt. 24, 1469–1475 (1985).
[CrossRef] [PubMed]

N. H. Farhat, D. Psaltis, “Optical Implementation of Associative Memory Based on Models of Neural Networks,” in Optical Signal Processing, J. L. Horner, Ed. (Academic, New York, 1987), pp. 129–162.

Jang, J.-S.

Jung, S.-W.

Lee, S.-Y.

Lu, T.

Macukow, B.

Paek, E. G.

Prata, A.

Psaltis, D.

N. H. Farhat, D. Psaltis, A. Prata, E. G. Paek, “Optical Implementation of the Hopfield Model,” Appl. Opt. 24, 1469–1475 (1985).
[CrossRef] [PubMed]

N. H. Farhat, D. Psaltis, “Optical Implementation of Associative Memory Based on Models of Neural Networks,” in Optical Signal Processing, J. L. Horner, Ed. (Academic, New York, 1987), pp. 129–162.

Shin, S.-Y.

Wu, S.

Xu, X.

Yang, X.

Yu, F. T. S.

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 (4)

Fig. 1
Fig. 1

Compact ONN architecture using cascaded LCTVs.

Fig. 2
Fig. 2

Display format of a 2-D input pattern and 4-D IWM: (a) input pattern; (b) IWM.

Fig. 3
Fig. 3

Experimental result for an autoassociative memory: (a) four capital letters stored in the IWM; (b) positive IWM; (c) negative IWM; (d) partial input pattern; (e) reconstructed pattern.

Fig. 4
Fig. 4

Experimental result for heteroassociative memory: (a) input–output training set; (b) positive IWM; (c) negative IWM; (d) partial input pattern; (e) output pattern.

Equations (1)

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

V l k ( n + 1 ) = f [ i = 1 N j = 1 N T l k i j U i j ( n ) ] ,

Metrics