DocumentCode :
3231158
Title :
Highly-parallel optical adaptive neural computers with layered and segmented structures
Author :
Lin, Freddie ; Savant, Gajendra ; Brown, Robert ; Kuo, Chai-Pei ; Jannson, Tomasz
Author_Institution :
Phys. Opt. Corp., Torrance, CA, USA
fYear :
1989
fDate :
0-0 1989
Firstpage :
487
Abstract :
In order to make highly parallel large-scale optical adaptive neural computers for recognition, vision, and other man-machine interface applications, a new technological approach to all-optic neurons and adaptive synapses of layered and segmented neural architectures is approached. Basic optical elements will be used in the proposed three-layer segmented neural architecture in which many fully interconnected neural nets are systematically connected to realize large-scale tasks. In other words, three-layer segmented neural computers have the ability to perform large-scale tasks for which pure fully interconnected neural computers would be physically unsuitable because of size consideration.<>
Keywords :
computer vision; computerised pattern recognition; optical information processing; parallel architectures; adaptive synapses; all-optic neurons; large-scale tasks; man-machine interface; optical adaptive neural computers; recognition; segmented structures; three-layer segmented neural computers; vision; Machine vision; Optical data processing; Parallel architectures; Pattern recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118287
Filename :
118287
Link To Document :
بازگشت