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.
@article{arxiv.1103.4487,
title = {Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs},
author = {Dan C. Cireşan and Ueli Meier and Luca M. Gambardella and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1103.4487},
year = {2011}
}