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

Neural-processing type optical wavelength demultiplexer using high-speed analog-neural-network integrated circuits

Not Accessible

Your library or personal account may give you access

Abstract

A neural-processing type optical WDM demultiplexer consisting of a multimode guide and an electrical neural network (NN) has been proposed.1 It features simple optical components, easy alignment, and modifiable characteristics because its neural parameters are electrically controllable. This paper reports the demultiplexing results at 150 Mb/s obtained by using the new analog neural network LSIs (ANN-LSIs) and the multimode planar waveguide.

© 1991 Optical Society of America

PDF Article
More Like This
Monolithically Integrated InP Photonic Circuits for Optical processing in Very High Speed Optical Loop

M. Renaud, J.A. Cavaillès, J.F. Vinchant, P. Jarry, M. Erman, T. Martinson, and P. Vogel
ThA3 Photonic Switching (PS) 1991

High-speed tuning of a neural control WDM demultiplexer

H. Miyao, S. Aisawa, F. Ito, and K. Noguchi
WL6 Optical Fiber Communication Conference (OFC) 1996

Multichannel optoelectronic integrated circuit receiver with switching function for wavelength-division multiplexing networks

L. A. Wang, R. Runge, W. P. Hong, and G. K. Chang
CThR53 Conference on Lasers and Electro-Optics (CLEO:S&I) 1991

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.