DocumentCode
2286812
Title
Statistical error modeling of CNN-UM architectures: the binary case
Author
Földesy, Péter
Author_Institution
Comput. & Autom. Res. Inst., Hungarian Acad. of Sci., Budapest, Hungary
fYear
2002
fDate
22-24 Jul 2002
Firstpage
467
Lastpage
474
Abstract
In this paper a detailed error model is analyzed of the CNN-UM in a general statistical manner. The locally regular template class is considered and the possibility of erroneous output is expressed from the component nonlinearity and parameter deviation.
Keywords
cellular neural nets; error statistics; neural chips; neural net architecture; CNN-UM architectures; binary input-output locally regular operations; component nonlinearity; erroneous output; locally regular template class; parameter deviation; statistical error modeling; Automation; Cellular neural networks; Computer aided software engineering; Computer architecture; Computer errors; Covariance matrix; Electronic mail; Gray-scale; Statistical analysis; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Cellular Neural Networks and Their Applications, 2002. (CNNA 2002). Proceedings of the 2002 7th IEEE International Workshop on
Print_ISBN
981-238-121-X
Type
conf
DOI
10.1109/CNNA.2002.1035085
Filename
1035085
Link To Document