Analog Optical Neural Nets: A Noise Sensitivity Analysis

Abstract

The development of analog optical implementations of neural networks such as the multilayer perceptron with learning by backward error propagation (BEP) requires an understanding of the noise sensitivity of such architectures. In this program computer simulations were used to study the effects of component and system noise on the performance of such optical implementations. A hybrid optical/electronic parallel architecture capable of both the forward pass and backward error propagation steps of training data presentation was conceived and modeled. The simulations showed that the most significant effects were due to the nonlinear response of the spatial light modulators used to store and update the neural weights. Another conclusion of the simulation results was that increasing the hidden layer size increases noise immunity significantly.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 11, 1991
Accession Number
ADA242920

Entities

People

  • James J. Levy
  • Michael W. Haney
  • Ravindra A. Athale

Organizations

  • Braddock Dunn & McDonald

Tags

Communities of Interest

  • Advanced Electronics
  • C4I
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Coding
  • Computational Science
  • Computer Programming
  • Computers
  • Detection
  • Detectors
  • Electrical Engineering
  • Information Processing
  • Information Systems
  • Machine Learning
  • Neural Networks
  • Optical Modulators
  • Pattern Recognition
  • Self Organizing Systems
  • Simulations

Fields of Study

  • Physics

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.
  • Quantum Dot Semiconductor Device Photonics and Graphene Optoelectronic Materials and THz Physics.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Microelectronics