Massively Deep Artificial Neural Networks for Handwritten Digit Recognition
Department of Computer Science, Aberystwyth University, Aberystwyth, Ceredigion
arXiv:1507.05053 [cs.CV], (17 Jul 2015)
@article{o’shea2015massively,
title={Massively Deep Artificial Neural Networks for Handwritten Digit Recognition},
author={O’Shea, Keiron},
year={2015},
month={jul},
archivePrefix={"arXiv"},
primaryClass={cs.CV}
}
Greedy Restrictive Boltzmann Machines yield an fairly low 0.72% error rate on the famous MNIST database of handwritten digits. All that was required to achieve this result was a high number of hidden layers consisting of many neurons, and a graphics card to greatly speed up the rate of learning.
July 24, 2015 by hgpu
