ImageNet Classification with Deep Convolutional Neural Networks

dc.contributor.authorKrizhevsky, Alex
dc.contributor.authorSutskever, Ilya
dc.contributor.authorHinton, Geoffrey E.
dc.date.accessioned2025-06-02T11:11:45Z
dc.date.available2025-06-02T10:42:49Z
dc.date.available2025-06-02T11:11:45Z
dc.date.issued2012-12-03
dc.descriptionAlexNet은 1.2백만 개의 ImageNet 이미지에 대해 대규모 CNN을 학습하여 당시 최첨단 수준의 분류 성능을 달성하였으며, 딥러닝 시대를 열었습니다 ©2012 NeurIPS Authors
dc.description.abstractWe 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.
dc.identifier.urihttps://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
dc.identifier.urihttp://data.inu.ac.kr/handle/123456789/1933.3
dc.language.isoen_US
dc.publisherNeurIPS
dc.relation.ispartofseries25
dc.titleImageNet Classification with Deep Convolutional Neural Networks
dc.title.alternativeCNN, AlexNet
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
NIPS-2012-imagenet-classification-with-deep-convolutional-neural-networks-Paper.pdf
Size:
1.35 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:

Collections

Version History

Now showing 1 - 3 of 3
VersionDateSummary
3*
2025-06-02 20:11:10
add sponsore and description
2025-06-02 20:04:54
add subject
2025-06-02 19:42:49
* Selected version