ImageNet classification with deep convolutional neural networks

Communications of the ACM - Tập 60 Số 6 - Trang 84-90 - 2017
Alex Krizhevsky1, Ilya Sutskever1, Geoffrey E. Hinton2
1Google Inc
2OpenAI

Tóm tắt

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%, respectively, 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.

Từ khóa


Tài liệu tham khảo

10.1145/1345448.1345465

Berg A., 2010, Large scale visual recognition challenge

10.1023/A:1010933404324

Cireşan D., 2011, High-performance neural networks for visual object classification. Arxiv preprint arXiv:1102.0183

Cireşan D., 2012, Multi-column deep neural networks for image classification. Arxiv preprint arXiv:1202.2745

Deng J. Berg A. Satheesh S. Su H. Khosla A. Fei-Fei L. In ILSVRC-2012 (2012). Deng J. Berg A. Satheesh S. Su H. Khosla A. Fei-Fei L. In ILSVRC-2012 (2012).

Deng J., 2009, CVPR09

10.1016/j.cviu.2005.09.012

10.1007/BF00344251

He K., 2015, Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385

Hinton G., 2012, Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580

10.1109/ICCV.2009.5459469

Krizhevsky A., 2009, Department of Computer Science

Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript

Krizhevsky A., 2011, ESANN

LeCun Y., 1990, Advances in Neural Information Processing Systems

LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)

10.5555/1896300.1896315

10.1109/ISCAS.2010.5537907

10.1145/1553374.1553453

10.1007/BF01931367

Mensink T., 2012, Italy

10.5555/3104322.3104425

10.1371/journal.pcbi.0040027

10.1371/journal.pcbi.1000579

Rumelhart D.E., 1985, DTIC Document

10.1007/s11263-007-0090-8

10.1109/CVPR.2011.5995504

10.5555/938980.939477

10.1109/CVPR.2015.7298594

10.1162/neco.2009.10-08-881

Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences

Thông tin
Thông tin xuất bản

Communications of the ACM

Tập 60 Số 6

84-90

Thông tin tác giả