Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

03/23/2011

∙

by   Dan C. Cireşan, et al.

∙

0

∙

share

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 significantly improve this result, using graphics cards to greatly speed up training of simple but deep MLPs, which achieved 0.35 previous more complex methods. Here we report another substantial improvement: 0.31