Convolutional Neural Network Committees for Handwritten Character Classification

Authors:
Dan Claudiu Ciresan;Ueli Meier;Luca Maria Gambardella;Jurgen Schmidhuber
Affiliations:
-;-;-;-
Venue:
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Year:
2011

Citing 0
Cited 3

2012 Special Issue: Multi-column deep neural network for traffic sign classification

Neural Networks
LoGID: An adaptive framework combining local and global incremental learning for dynamic selection of ensembles of HMMs

Pattern Recognition
Unconstrained handwritten Devanagari character recognition using convolutional neural networks

Proceedings of the 4th International Workshop on Multilingual OCR

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.