English

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

Machine Learning 2011-03-24 v1 Artificial Intelligence Computer Vision and Pattern Recognition Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@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}
}

Comments

9 pages, 4 figures, 3 tables