2011 International Conference on Document Analysis and Recognition (2011)
Sept. 18, 2011 to Sept. 21, 2011
In 2010, after many years of stagnation, the MNIST handwriting recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performance. We also apply the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters. A committee of seven CNNs obtains the best results published so far for both NIST digits and NIST letters. The robustness of our method is verified by analyzing 78125 different 7-net committees.
Convolutional Neural Networks, Graphics Processing Unit, Handwritten Character Recognition, Committee
D. C. Ciresan, L. M. Gambardella, U. Meier and J. Schmidhuber, "Convolutional Neural Network Committees for Handwritten Character Classification," 2011 International Conference on Document Analysis and Recognition(ICDAR), Beijing, China, 2011, pp. 1135-1139.