ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks
复制标题
DOI：
10.1145/3065386
复制
发表时间：
2017-06-01
影响因子：
22.7
通讯作者：
Hinton, Geoffrey E.
中科院分区：
文献类型：
--
作者：
Krizhevsky, Alex;Sutskever, Ilya;Hinton, Geoffrey E.
我们训练了一个大型的深度卷积神经网络，将ImageNet LSVRC-2010竞赛中的120万张高分辨率图像分类为1000个不同的类别。在测试数据上，我们实现了前1和前5的错误率分别为37.5%和17.0%，这比以前的最先进水平要好得多。神经网络有6000万个参数和650，000个神经元，由五个卷积层组成，其中一些层后面是最大池层，以及三个完全连接的层，最后是1000路softmax。为了加快训练速度，我们使用了非饱和神经元和非常高效的卷积运算GPU实现。为了减少全连接层中的过拟合，我们采用了一种最近开发的正则化方法，称为“dropout”，该方法被证明非常有效。我们还在ILSVRC-2012竞赛中输入了该模型的变体，并获得了15.3%的前5名测试错误率，而第二名的错误率为26.2%。
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.