ImageNet classification with deep convolutional neural networks

Testo completo ad accesso aperto Verifica disponibilità: Testo completo (sito dell'editore)

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.

Salvato in:
Autori: 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))
Pubblicato in: Communications of the ACM, vol. 60, n. 6, pp. 84-90
Data di pubblicazione:24/05/2017
Editore:Association for Computing Machinery
Tipo di documento:Articolo
Lingua:inglese
DOI: 10.1145/3065386
ISSN:0001-0782, 1557-7317
Accesso aperto: Accesso aperto Bronze: lettura gratuita presso l'editore, senza licenza aperta – Communications of the ACM
Citazioni ricevute:112.116
Soggetti:
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
Identificativi: OpenAlex W2163605009

Dati dell'indice centrale: OpenAlex (licenza CC0).

Riassunto: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