论文资源：
https://zhuanlan.zhihu.com/p/433682901
https://zhuanlan.zhihu.com/p/664371926
https://zhuanlan.zhihu.com/p/430432370
https://zhuanlan.zhihu.com/p/512579984
https://zhuanlan.zhihu.com/p/420712916
https://zhuanlan.zhihu.com/p/487522053
-----------------------------------------------------
论文题目：ImageNet Classification with Deep Convolutional Neural Networks
生词：
Classification：分类器
Abstract
（1）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.
翻译：我们训练了一个大的深度卷积神经网络，它可以将ImagenNet竞赛的120万高清图片归类到成1000中不同的种类中。
生词：
deep convolutional neural network：深度卷积神经网络
high-resolution：高分辨率的
contest：竞赛
（2）On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art.
翻译：针对测试数据，我们达成了37.5%和17%的错误率，名列第一和第五，这比以前的最高值好了太多了。
生词：
condiderably：相当地
the previous state-of-the-art：以前的最好值
（3）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.
翻译：
To make train- ing 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.
