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

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

2011-03-23

arxiv.org/abs/1103.4487v1

Computer Science

Learning

9 pages, 4 figures, 3 tables

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-441183