DocumentCode :
2735321
Title :
Shape recognition with nearest neighbor isomorphic network
Author :
Yau, Hung-Chun ; Manry, Michael T.
Author_Institution :
Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
fYear :
1991
fDate :
8-14 Jul 1991
Abstract :
Summary form only given. The nearest-neighbor isomorphic network (NNIN) paradigm is a combination of sigma-pi units in the hidden layer and product units in the output layer. Good initial weights can be found through clustering of the input training vectors, and the network can be successfully trained via back-propagation (BP) learning. Theoretical conditions under which the product operation can replace the Min operation were found. Under some sufficient conditions, the product operation yields the same classification result as the Min operation. The algorithm was applied to a geometric shape recognition problem, and the performances were compared with those of two other well-known algorithms
Keywords :
computerised pattern recognition; neural nets; Min operation; back-propagation (BP) learning; classification; geometric shape recognition; hidden layer; input training vectors; nearest neighbor isomorphic network; output layer; product operation; product units; sigma-pi units; Computed tomography; Gray-scale; Intelligent networks; Micromotors; Nearest neighbor searches; Neural networks; Performance evaluation; Shape; Sufficient conditions; X-ray imaging;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
Type :
conf
DOI :
10.1109/IJCNN.1991.155527
Filename :
155527
Link To Document :
بازگشت