Massively Deep Artificial Neural Networks for Handwritten Digit Recognition
Keiron O’Shea · arXiv (Cornell University) · 2015
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.