DocumentCode
2250913
Title
CNNOPT: Learning dynamics and CNN chip-specific robustness
Author
Hillier, Daniel ; de Souza, Samuel Xavier ; Suykens, Johan A K ; Vandewalle, Joos
fYear
2006
fDate
Aug. 2006
Firstpage
1
Lastpage
1
Abstract
A software tool with the aim of learning new CNN templates and incorporating the ability to tune templates to individual chip instances is presented. During demonstration, the training process of the grayscale constrained trigger-wave template [1] will be shown. The audience can test the tool by proposing their own operation to be learned/tuned.
Keywords
Cellular neural networks; Cost function; Gray-scale; Laboratories; Microwave integrated circuits; Neural networks; Optimization methods; Robustness; Spatiotemporal phenomena; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Cellular Neural Networks and Their Applications, 2006. CNNA '06. 10th International Workshop on
Conference_Location
Istanbul, Turkey
Print_ISBN
1-4244-0640-4
Electronic_ISBN
1-4244-0640-4
Type
conf
DOI
10.1109/CNNA.2006.341591
Filename
4145831
Link To Document