A weight discretization paradigm for optical neural networks 0

  title={A weight discretization paradigm for optical neural networks 0},
  author={Emile Fiesler and Amar Choudry and H. J. Caul eld},
Neural networks are a primary candidate architecture for optical computing. One of the major problems in using neural networks for optical computers is that the information holders: the interconnection strengths (or weights) are normally real valued (continuous), whereas optics (light) is only capable of representing a few distinguishable intensity levels (discrete). In this paper a weight discretization paradigm is presented for back(ward error) propagation neural networks which can work with… CONTINUE READING
Highly Cited
This paper has 25 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 15 extracted citations

Enabling High-Performance , Mixed-Signal Approximate Computing by

Renee Marie St Amant
View 20 Excerpts
Highly Influenced

General-purpose code acceleration with limited-precision analog computation

2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA) • 2014
View 15 Excerpts
Highly Influenced

A Genetic-Algorithm-Based Weight Discretization Paradigm for Neural Networks

2009 WRI World Congress on Computer Science and Information Engineering • 2009

Optimization of neural network with fixed-point weights and touch-screen calibration

2009 4th IEEE Conference on Industrial Electronics and Applications • 2009

Research on Real-Time Image Sharpening Methods Based on Optimized Neural Network

2009 Fifth International Conference on Natural Computation • 2009


Publications referenced by this paper.
Showing 1-9 of 9 references

eld, Jason Kinser, and Steven K

H. John Cau
Rogers, Optical Neural Networks, Proceedings of the IEEE, volume 77, number 10, pages 1573-1583, October • 1989


E. Fiesler
Choudry, and H.J. Caul eld, "Weight discretization in backward error propagation neural networks", presented at the First Annual Meeting of the International Neural Network Society, Boston, Mas sachusetts, September 5-10, 1988, abstract: Neural networks, volume1, supplement 1, page 380, • 1988

Neural Networks Primer", part II, AI Expert, volume 3, number

Maureen Caudill

Athale, "E ects of noise on an Optical Implementation of an Addi tive Lateral Inhibitory Network", Proceedings of the IEEE rst international conference on neural networks, volume III, pages 615-623

Charles W. Stirk, R.A.S.M. Rovnyak
editors: Maureen Caudill and Charles Butler, • 1987


N. H. Farhat
Miyahara and, K.S. Lee, "Optical analog of two-dimensional neural networks and their application in recognition of radar targets", Neural networks for computing, American Institute of Physics (A.I.P.) conference proceedings 151, pages 146-152, editor: John S. Denker, at: Snowbird, Utah, April 13-1 • 1986

Hop eld, "Neural networks and physical systems with emergent collective computational abilities

J. John
Proceedings of the National Academy of Sciences of the U.S.A., • 1982

Beyond regression: New tools for prediction and analysis in the behavioral sciences

Paul Werbos
Ph.D. dissertation, Harvard University, • 1974

Similar Papers

Loading similar papers…