14301

Massively Deep Artificial Neural Networks for Handwritten Digit Recognition

Keiron O’Shea
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}

}

Download Download (PDF)   View View   Source Source   

555

views

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.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: