ImageNet Classification with Deep Convolutional Neural Networks

ImageNet Classification with Deep Convolutional Neural Networks. Krizhevsky, A., Sutskever, I., & Hinton, G. E In Advances in Neural Information Processing Systems, volume 25, 2012. Curran Associates, Inc..

Paper abstract bibtex 9 downloads

We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7\% and 18.9\% which is considerably better than the previous state-of-the-art results. The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and two globally connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets. To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective.

@inproceedings{krizhevsky_imagenet_2012,
	title = {{ImageNet} {Classification} with {Deep} {Convolutional} {Neural} {Networks}},
	volume = {25},
	url = {https://proceedings.neurips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html},
	abstract = {We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7{\textbackslash}\% and 18.9{\textbackslash}\% which is considerably better than the previous state-of-the-art results. The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and two globally connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets. To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective.},
	urldate = {2026-07-02},
	booktitle = {Advances in {Neural} {Information} {Processing} {Systems}},
	publisher = {Curran Associates, Inc.},
	author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
	year = {2012},
}

Downloads: 9