ImageNet classification with deep convolutional neural networks

TLDR

We trained a 60‑million‑parameter deep convolutional network with five convolutional layers, three fully connected layers, dropout regularization, non‑saturating activations, and a GPU‑accelerated implementation to classify 1.2 million ImageNet images into 1,000 classes. The model achieved 37.5 % top‑1 and 17.0 % top‑5 error on ImageNet, surpassing prior state‑of‑the‑art, and won ILSVRC‑2012 with a 15.3 % top‑5 error versus 26.2 % for the runner‑up.

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.