DocumentCode :
3288864
Title :
Gram-Schmidt orthogonalization neural nets for OCR
Author :
Szu, Harold ; Scheff, Kim
Author_Institution :
US Naval Res. Lab., Washington, DC, USA
fYear :
1989
fDate :
0-0 1989
Firstpage :
547
Abstract :
A description is given of a three-layer neural network for pattern classification/character recognition. The first layer is a heteroassociative feedforward network with bipolar output (+or-1) and zero threshold neurons. The second layer is an autoassociative memory whose input-output characteristics are the same as those in the first layer. The third layer is used to recognize the pattern and control whether the new orthogonal feature vector should be installed by the outer product formula to increase the memory capacity to M´=M+1. With this network, conventional pattern recognition of the minimax type is used to determine the initial interconnection matrix. The samples are classified by means of supervised learning. Only a single physical layer need be built, since the same layer can repeatedly be used three times in series. The performance of the network is studied.<>
Keywords :
minimax techniques; neural nets; optical character recognition; Gram-Schmidt orthogonalization neural nets; OCR; autoassociative memory; bipolar output; heteroassociative feedforward network; interconnection matrix; minimax; optical character recognition; pattern recognition; zero threshold neurons; Minimax methods; Neural networks; Optical character 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.1989.118632
Filename :
118632
Link To Document :
بازگشت