Imagenet classification with deep convolutional neural networks

DMCA

Imagenet classification with deep convolutional neural networks

Cached

Download Links

by Alex Krizhevsky , Ilya Sutskever , Geoffrey E. Hinton

Venue:	Advances in Neural Information Processing Systems
Citations:	1008 - 11 self

BibTeX

@INPROCEEDINGS{Krizhevsky_imagenetclassification,
    author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton},
    title = {Imagenet classification with deep convolutional neural networks},
    booktitle = {Advances in Neural Information Processing Systems},
    year = {},
    pages = {2012}
}

OpenURL

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. 1

Keyphrases

deep convolutional neural network imagenet classification fully-connected layer previous state-of-the-art second-best entry ilsvrc-2012 competition convolution operation test data different class final 1000-way softmax neural network non-saturating neuron max-pooling layer convolutional layer top-5 test error rate efficient gpu implementation recently-developed regularization method high-resolution image imagenet lsvrc-2010 contest top-5 error rate

DMCA