We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5\% and 17.0 \% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called ” dropout” that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3\%, compared to 26.2 \% achieved by the second-best entry.
%0 Journal Article
%1 krizhevsky2012imagenet
%A Krizhevsky, Alex
%A Sutskever, Ilya
%A Hinton, Geoffrey E.
%D 2012
%E Bartlett, P.
%E Pereira,
%E Burges,
%E Bottou, L.
%E Weinberger,
%J Advances in Neural Information Processing Systems
%K imported
%P 1106--1114
%T ImageNet Classification with Deep Convolutional Neural Networks
%U https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
%V 25
%X We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5\% and 17.0 \% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called ” dropout” that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3\%, compared to 26.2 \% achieved by the second-best entry.
@article{krizhevsky2012imagenet,
abstract = {{We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5\% and 17.0 \% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called ” dropout” that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3\%, compared to 26.2 \% achieved by the second-best entry.}},
added-at = {2017-07-19T15:29:59.000+0200},
author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
biburl = {https://www.bibsonomy.org/bibtex/2e477bd5d3cf2147a5ddba524d9184fff/andreashdez},
citeulike-article-id = {14025633},
citeulike-linkout-0 = {https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf},
editor = {Bartlett, P. and Pereira and Burges and Bottou, L. and Weinberger},
interhash = {74bbb5dea5afb1b088bd10e317f1f0d2},
intrahash = {e477bd5d3cf2147a5ddba524d9184fff},
journal = {Advances in Neural Information Processing Systems},
keywords = {imported},
pages = {1106--1114},
posted-at = {2016-05-01 21:41:10},
priority = {2},
timestamp = {2017-07-19T15:31:02.000+0200},
title = {{ImageNet Classification with Deep Convolutional Neural Networks}},
url = {https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf},
volume = 25,
year = 2012
}