Stochastic Gradient Descent Training of Ensembles of DT-CNN Classifiers for Digit Recognition
Christian Merkwirth, MACIEJ J. OGORZAŁEK, Joerg Wichard, Maciej Ogorzałek, Zbigniew Galias, Bartłomiej Kadeja, Bartłomiej Kadeja · Max Planck Institute for Plasma Physics · 2003
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 using concepts and techniques from Machine Learning, we can outperform Support Vector Machines (SVM) on this problem.