Parametrical Neural Networks and Some Other Similar Architectures

2006/08/18 by Leonid B. Litinskii, Litinskii, Leonid B.
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.NE

paper · pdf · doi:10.48550/arxiv.cs/0608073

15 pages, 2 figures, accepted for publication in "Optical Memory & Neural Networks" (2006)

arxiv created 2006/08/18 · arxiv updated 2009/12/01

Abstract

A review of works on associative neural networks accomplished during last four years in the Institute of Optical Neural Technologies RAS is given. The presentation is based on description of parametrical neural networks (PNN). For today PNN have record recognizing characteristics (storage capacity, noise immunity and speed of operation). Presentation of basic ideas and principles is accentuated.

Related

• Parametrical Neural Network
• Operator formalism for optical neural network based on the parametrical four-wave mixing process
• Artificial Neural Networks and their Applications
• Vector-Neuron Models of Associative Memory
• Attractor Neural Networks