next up previous contents
Next: The Stanford / Technicolor Up: Summary of References Related Previous: Learning hierarchical features for   Contents

Subsections

ImageNet Classification with Deep Convolutional Neural Networks [50]

Original Abstract

We trained a large, deep convolutional neural network to classify the 1.2 millionhigh-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif-ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5

Main points


next up previous contents
Next: The Stanford / Technicolor Up: Summary of References Related Previous: Learning hierarchical features for   Contents
Miquel Perello Nieto 2014-11-28