ImageNet classification with deep convolutional neural networks

Open access full text Check availability: Full text (publisher site)

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%, 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.

Saved in:
Authors: Alex Krizhevsky (Google (United States); University of Toronto); Ilya Sutskever (Google (United States); University of Toronto); Geoffrey E. Hinton (University of Toronto; OpenAI (United States))
Published in: Communications of the ACM, vol. 60, no. 6, pp. 84-90
Publication date:24/05/2017
Publisher:Association for Computing Machinery
Document type:Article
Language:English
DOI: 10.1145/3065386
ISSN:0001-0782, 1557-7317
Open access: Open access Bronze: free to read at the publisher, without an open license – Communications of the ACM
Cited by:112,116
Subjects:
Advanced Neural Network Applications (Physical Sciences > Computer Science > Computer Vision and Pattern Recognition)
Domain Adaptation and Few-Shot Learning (Physical Sciences > Computer Science > Artificial Intelligence)
Advanced Image and Video Retrieval Techniques (Physical Sciences > Computer Science > Computer Vision and Pattern Recognition)
ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
Identifiers: OpenAlex W2163605009

Central index data: OpenAlex (CC0 license).

Summary: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.
ISSN:0001-0782
1557-7317
DOI:10.1145/3065386