Programmable Optical Quadratic Neural Networks
Abstract
Analytical and experimental investigations of optical quadratic neural networks have been conducted. Results reported include: (1)Development of a polarization-based outer product processor implementing a quadratic neural network, (2) implementation of a photorefractive crystal based quadratic neural network utilizing feedback for learning, (3) derivation of a statistical parameter which can be used to completely characterize the behavior of linear and higher order Hopfield associative memories and (4) development of a method to reduce the number of interconnections in associative memories while retaining good performance.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1991
- Accession Number
- ADA233520
Entities
People
- John F. Walkup
- Thomas F. Krile
Organizations
- Texas Tech University