Communications of the ACM· 2017Q1
ImageNet classification with deep convolutional neural networks
- 75,715citations
- Q1SCImago
- 2017year
Short summary
A deep convolutional neural network achieved state-of-the-art ImageNet classification, reducing top-5 error rates to 17.0% in 2010 and a winning 15.3% in 2012.
AI-generated from the title and abstract; the full text is not read.
Key points
- Achieved 17.0% top-5 error rate on ImageNet LSVRC-2010, a significant improvement over prior methods.
- A variant of the network won the ILSVRC-2012 competition with a 15.3% top-5 error rate, substantially better than the second-place entry (26.2%).
- The network architecture comprises five convolutional layers, max-pooling, and three fully connected layers with a 1000-way softmax output.
- Employed techniques like non-saturating neurons, efficient GPU convolution, and dropout regularization for faster training and reduced overfitting.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source. Communications of the ACM, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science