Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
IDSIA / USI-SUPSI, Dalle Molle Institute for Artificial Intelligence, Galleria 2, 6928 Manno, Switzerland
arXiv:1103.4487v1 [cs.LG] (23 Mar 2011)
@article{2011arXiv1103.4487C,
author={Cire{c s}an}, D.~C. and {Meier}, U. and {Gambardella}, L.~M. and {Schmidhuber}, J.},
title={"{Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs}"},
journal={ArXiv e-prints},
archivePrefix={"arXiv"},
eprint={1103.4487},
primaryClass={"cs.LG"},
keywords={Computer Science – Learning, Computer Science – Artificial Intelligence, Computer Science – Computer Vision and Pattern Recognition, Computer Science – Neural and Evolutionary Computing},
year={2011},
month={mar},
adsurl={http://adsabs.harvard.edu/abs/2011arXiv1103.4487C},
adsnote={Provided by the SAO/NASA Astrophysics Data System}
}
The competitive MNIST handwritten digit recognition benchmark has a long history of broken records since 1998. The most recent substantial improvement by others dates back 7 years (error rate 0.4%) . Recently we were able to significantly improve this result, using graphics cards to greatly speed up training of simple but deep MLPs, which achieved 0.35%, outperforming all the previous more complex methods. Here we report another substantial improvement: 0.31% obtained using a committee of MLPs.
June 10, 2011 by hgpu
