Title :
SCNN: a universal simulator for cellular neural networks
Author :
Kunz, R. ; Tetzlaff, R. ; Wolf, D.
Author_Institution :
Inst. fur Angewandte Phys., Frankfurt Univ., Germany
Abstract :
In this paper a universal simulator for cellular neural network (CNN) is presented. CNN with nonlinear and delay-type templates can be simulated precisely with SCNN, practically without any limitations. Furthermore different training algorithms for networks with translation variant and invariant templates are implemented in SCNN. As an example, parameter deviations of a template have been reduced by training. Simulation and training results are discussed in detail
Keywords :
backpropagation; cellular neural nets; image processing; simulation; virtual machines; SCNN; Unix; backpropagation; cellular neural networks; delay-type templates; image processing; invariant templates; nonlinear templates; parameter deviations; universal simulator; Backpropagation algorithms; Cellular neural networks; Computational modeling; Delay; Equations; Hardware; Image processing; Personal communication networks; Signal processing; Testing;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566570
