Photonic Technology Development for Densely-Interconnected Neural Networks.

Abstract

Progress on the grant, 'Photonic Technology Development for Densely Interconnected Neural Networks', is described. Substantial progress has been made in the following areas. Artificial neural network models (or implementation using photonics have been developed and analyzed. Radial basis function neural networks for analog nonparametric density function estimation and pattern recognition, and multilayer backward error propagation neural networks both for implementation on photonic hardware, have been characterized. Emphasis has been on implementations based on incoherent/coherent double angular multiplexed volume hologram interconnected architectures using photorefractive materials, 2-D source arrays, and optoelectronic spatial light modulators, are emphasized. Our work on optoelectronic smart pixel array spatial light modulators is also summarized. Silicon chips for arrays of neuron unit processing with optical inputs have been fabricated, as have GaAs-based chips incorporating inverted Fabry Perot cavity strained layer multiple quantum well modulators. Experimental results from are given. Results of flip chip bonding using a newly developed Velcro like indium bump bond process are given as well. Also included in this report are personnel supported, lists of publications and presentations, transitions to industry, and patent disclosures.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 27, 1997
Accession Number
ADA322315

Entities

People

  • A. Madhukar
  • Armand R. Tanguay Jr.
  • B. K. Jenkins

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Advanced Electronics

DTIC Thesaurus Topics

  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Flip Chips
  • Materials
  • Modulators
  • Neural Networks
  • Optical Materials
  • Optical Modulators
  • Pattern Recognition
  • Photonics
  • Photorefractive Materials
  • Quantum Wells
  • Recognition
  • Signal Processing
  • Two Dimensional

Readers

  • Integrated Circuit Design and Technology.
  • Neural Network Machine Learning.
  • Optical Physics and Photonics.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Microelectronics
  • Quantum Computing