ImageNet classification with deep convolutional neural networks. Krizhevsky, A., Sutskever, I., & Hinton, G. E. Communications of the ACM, 60(6):84–90, May, 2017.
ImageNet classification with deep convolutional neural networks [link]Paper  doi  abstract   bibtex   
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{krizhevsky_imagenet_2017,
	title = {{ImageNet} classification with deep convolutional neural networks},
	volume = {60},
	issn = {0001-0782, 1557-7317},
	url = {https://dl.acm.org/doi/10.1145/3065386},
	doi = {10.1145/3065386},
	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.},
	language = {en},
	number = {6},
	urldate = {2022-03-02},
	journal = {Communications of the ACM},
	author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
	month = may,
	year = {2017},
	pages = {84--90},
}

Downloads: 0