DocumentCode
2694577
Title
Character recognition using a dynamic opto-electronic neural network with unipolar binary weights
Author
Oita, Masaya ; Takahashi, Masanobu ; Tai, Shuichi ; Kojima, Keisuke ; Kyuma, Kazuo
fYear
1990
fDate
17-21 June 1990
Firstpage
789
Abstract
A novel quantized learning rule with unipolar binary weights which is useful to simplify the artificial neural hardware is reported. An input-dependent thresholding operation is also proposed to remove the unwanted effect due to insufficient contrast ratio of spatial light modulations as a synaptic connection device. The recognition of 26 characters of the alphabet by the single set of an optoelectronic three-layered network was demonstrated experimentally
Keywords
character recognition; learning systems; neural nets; optical information processing; optoelectronic devices; artificial neural hardware; character recognition; learning rule; opto-electronic neural network; synaptic connection device; three-layered network; unipolar binary weights;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location
San Diego, CA, USA
Type
conf
DOI
10.1109/IJCNN.1990.137665
Filename
5726625
Link To Document