TY - GEN
T1 - Convolutional neural network committees for handwritten character classification
AU - Cireşan, Dan Claudiu
AU - Meier, Ueli
AU - Gambardella, Luca Maria
AU - Schmidhuber, Jürgen
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 2011/12/2
Y1 - 2011/12/2
N2 - 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. © 2011 IEEE.
AB - 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. © 2011 IEEE.
UR - http://ieeexplore.ieee.org/document/6065487/
UR - http://www.scopus.com/inward/record.url?scp=82355186196&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2011.229
DO - 10.1109/ICDAR.2011.229
M3 - Conference contribution
SN - 9780769545202
SP - 1135
EP - 1139
BT - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
ER -