Dense Modifiable Interconnections Utilizing Photorefractive Volume Holograms

Abstract

This report describe an experimental two-layer optical neural network built at Caltech. The system uses photorefractive volume holograms to implement dense, modifiable synaptic interconnections and liquid crystal light valves (LCVS) to perform nonlinear thresholding operations. Kanerva's Sparse, Distributed Memory was implemented using this network and its ability to recognize handwritten character-alphabet (A-Z) has been demonstrated experimentally. According to Kanerva's model, the first layer has fixed, random weights of interconnections and the second layer is trained by sum-of-outer-products rule. After training, the recognition rates of the network on the training set (104 patterns ) and test set (520 patterns) are 100% and 50%, respectively.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 30, 1990
Accession Number
ADA230164

Entities

People

  • Demetri Psaltis
  • Yong Qiao

Organizations

  • California Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Alphabets
  • California
  • Crystals
  • Electrical Engineering
  • Engineering
  • Holograms
  • Identification
  • Laser Beams
  • Lasers
  • Liquid Crystals
  • Neural Networks
  • Notation
  • Optical Correlators
  • Personality
  • Recognition
  • Refractive Index
  • Training

Fields of Study

  • Physics

Readers

  • Image Processing and Computer Vision.
  • Nanofabrication and Microfabrication.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks