Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

An adaptive resonance neural network implementation utilizing phase conjugation

Not Accessible

Your library or personal account may give you access

Abstract

A novel adaptive resonance (ART) device, based on holographic information processing in a phase-conjugating crystal, allows pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams. A reset mechanism allows an ART search strategy by rejecting beams as needed. The design is inspired by a non-learning optical associative memory, the holographic optical resonator,1 but does learn and uses information the other device discards. The learning capability results from replacing the resonator’s fixed hologram with a barium titanate crystal. This device offers higher information storage density than do alternative ART implementations.2-5

© 1992 Optical Society of America

PDF Article
More Like This
Optical implementations of adaptive-resonance-theory neural architectures

Thomas P. Caudell
TuW.1 OSA Annual Meeting (FIO) 1993

Programmable optical neural networks

Yuri Owechko
MD2 OSA Annual Meeting (FIO) 1992

Neural network adaptive wavelet transform

Harold Szu
FA3 OSA Annual Meeting (FIO) 1992

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.