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 Conference Paper
%1 krizhevsky2012imagenet
%A Krizhevsky, Alex
%A Sutskever, Ilya
%A Hinton, Geoffrey E
%B Advances in neural information processing systems
%D 2012
%K classification cnn image imagenet
%P 1097--1105
%T Imagenet classification with deep convolutional neural networks
%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.
@inproceedings{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 = {2017-02-26T17:53:42.000+0100},
author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
biburl = {https://www.bibsonomy.org/bibtex/2784f6d0ddce5f78d5d2105a1781cecc2/nosebrain},
booktitle = {Advances in neural information processing systems},
interhash = {74bbb5dea5afb1b088bd10e317f1f0d2},
intrahash = {784f6d0ddce5f78d5d2105a1781cecc2},
keywords = {classification cnn image imagenet},
pages = {1097--1105},
timestamp = {2017-02-26T17:54:48.000+0100},
title = {Imagenet classification with deep convolutional neural networks},
year = 2012
}