Massively Deep Artificial Neural Networks for Handwritten Digit Recognition

2015/07/17 by O'Shea, Keiron
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1507.05053

Abstract

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.

Related

• Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
• NeuroWrite: Predictive Handwritten Digit Classification using Deep Neural Networks
• Handwritten Digits Recognition using Deep Convolutional Neural Network: An Experimental Study using EBlearn
• Large-scale Artificial Neural Network: MapReduce-based Deep Learning
• A contextual analysis of multi-layer perceptron models in classifying hand-written digits and letters: limited resources