Skip to main content

Limitations of opto-electronic neural networks

Publication ,  Journal Article
Yu, J; Johnston, A; Psaltis, D; Brady, D
Published in: Proceedings of SPIE - The International Society for Optical Engineering
June 29, 1989

Neural networks are composed of three components: Neurons, weights, and connections. Limitation on implementing these components in electronics and optics are discussed. We show that using electronically fabricated neurons and a combination of optics and electronics for the weights and connections efficiently utilizes the advantage of each technology. The choice of the technology used to implement the weights and connections depends on the type of neural network being built. © 1989 SPIE.

Duke Scholars

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

EISSN

1996-756X

ISSN

0277-786X

Publication Date

June 29, 1989

Volume

1053

Start / End Page

40 / 51

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Yu, J., Johnston, A., Psaltis, D., & Brady, D. (1989). Limitations of opto-electronic neural networks. Proceedings of SPIE - The International Society for Optical Engineering, 1053, 40–51. https://doi.org/10.1117/12.951514
Yu, J., A. Johnston, D. Psaltis, and D. Brady. “Limitations of opto-electronic neural networks.” Proceedings of SPIE - The International Society for Optical Engineering 1053 (June 29, 1989): 40–51. https://doi.org/10.1117/12.951514.
Yu J, Johnston A, Psaltis D, Brady D. Limitations of opto-electronic neural networks. Proceedings of SPIE - The International Society for Optical Engineering. 1989 Jun 29;1053:40–51.
Yu, J., et al. “Limitations of opto-electronic neural networks.” Proceedings of SPIE - The International Society for Optical Engineering, vol. 1053, June 1989, pp. 40–51. Scopus, doi:10.1117/12.951514.
Yu J, Johnston A, Psaltis D, Brady D. Limitations of opto-electronic neural networks. Proceedings of SPIE - The International Society for Optical Engineering. 1989 Jun 29;1053:40–51.

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

EISSN

1996-756X

ISSN

0277-786X

Publication Date

June 29, 1989

Volume

1053

Start / End Page

40 / 51

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering