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

Optical neural network using pocket-sized liquid-crystal televisions

Not Accessible

Your library or personal account may give you access

Abstract

The improvements in liquid-crystal-television (LCTV) technology have made it possible to build a miniature optical neural network using high-resolution LCTV's to replace the cathode-ray-tube video monitor.1 Two LCTV's built by thin-film-transistor techniques have been used in an optical neural network for displaying the associative-memory matrix and input pattern, respectively. A compact optical neural network of 8 × 8 = 64 neurons has been synthesized, and the number of neurons in the network can be further increased to 15 × 20 = 300. The size of the optical neural network is only ~65 × 12 × 12 cm3, and the system size can be further reduced to ~20 × 7 × 7 cm3 by employing smaller LCTV's. The processing speed of the neural network can be as high as 3 × 106 interconnections.

© 1990 Optical Society of America

PDF Article
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.