Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
Dan Cireşan, Ueli Meier, Luca Maria Gambardella, Schmidhuber, Jürgen · arXiv (Cornell University) · 2011
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.