Title :
An unsupervised training rule for dynamic information processing
Author :
Haghighi, Siamack ; Akers, Lex A.
Author_Institution :
Intel. Corp., Chandler, AZ, USA
Abstract :
The authors have derived an unsupervised training rule for multilayered neural networks. The adaptive weight values are selected to maximize the fraction of a node output variance due to correlations among inputs. The processing units are not required to be fully connected. Applications of this training rule in image processing, including edge extraction, picture segmentation, multirepresentation, and motion detection, are presented
Keywords :
computerised picture processing; neural nets; training; adaptive weight values; dynamic information processing; edge extraction; image processing; motion detection; multilayered neural networks; multirepresentation; node output variance; picture segmentation; training rule; unsupervised training rule; Data mining; Image edge detection; Image processing; Image segmentation; Information processing; Motion detection; Neural networks; Pattern recognition; Power measurement; Solid state circuits;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155247
