Summary

International Symposium on Nonlinear Theory and its Applications

2005

Session Number:1-2-1

Session:

Number:1-2-1-1

Can DT-CNN Classifiers outperform SVM?

Christian Merkwirth,  Jochen Brocker,  Jorg Wichard,  Maciej Ogorza?ek,  

pp.557-560

Publication Date:2005/10/18

Online ISSN:2188-5079

DOI:10.34385/proc.40.1-2-1-1

PDF download (83.4KB)

We show how to train Discrete Time Cellular Neural Networks (DT-CNN) successfully by backpropagation to perform pattern recognition on a data set of handwritten digits. By employing concepts and techniques from Statistical Learning, we can obtain results outperforming that of a polynomial Support Vector Machine (SVM).