大家好，我是小P，今天給大家帶來經典深度學習論文翻譯的第一篇，中英對照。對“對象檢測”感興趣的小夥伴，歡迎加入對象檢測羣813221712討論和交流，進羣請看羣公告！
說明：由於CSDN排版的原因，此處就只上傳了一部分樣例，完整版word文檔請百度雲盤下載或進羣羣文件下載，敬請諒解！
百度雲鏈接：鏈接：https://pan.baidu.com/s/13oM8O_1VbG5Py9c-cMV2_A 密碼：myqc
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky University of Toronto [email protected]
Ilya Sutskever University of Toronto [email protected]
GeoffreyE. Hinton University of Toronto [email protected]
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% 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.
本文訓練了一個大規模的深度卷積神經網絡來將ImageNet LSVRC-2010比賽中的包含120萬幅高分辨率的圖像數據集分爲1000種不同類別。在測試集上，本文所得的top-1和top-5錯誤率分別爲37.5%和17.0%，該測試結果大大優於當前的最佳水平。本文的神經網絡包含6千萬個參數和65萬個神經元，包含了5個卷積層，其中有幾層後面跟着最大池化（max-pooling）層，以及3個全連接層，最後還有一個1000路的softmax層。爲了加快訓練速度，本文使用了不飽和神經元以及一種高效的基於GPU的卷積運算方法。爲了減少全連接層的過擬合，本文采用了最新的正則化方法“dropout”，該方法被證明非常有效。我們以該模型的變體參加了ILSVRC-2012比賽，相比第二名26.2%，我們以15.3%的top-5測試錯誤率獲勝。
…
…
Figure 2: An illustration of the architecture of our CNN, explicitly showing the delineation of responsibilities between the two GPUs. One GPU runs the layer-parts at the top of the figure while the other runs the layer-parts at the bottom. The GPUs communicate only at certain layers. The network’s inputis150,528-dimensional, and the number of neurons in the network’s remaining layers is given by 253,440–186,624–64,896–64,896–43,264– 4096–4096–1000.
圖2 本文CNN的結構圖示，明確地描述了兩個GPU之間的職責。一個GPU運行圖上方的層，另一個運行圖下方的層。兩個GPU只在特定的層通信。網絡的輸入是150,528維的，網絡剩餘層中的神經元數目分別是253440，186624，64896，64896，43264，4096，4096，1000
…
…
References
[1] R.M.BellandY.Koren.Lessons from the net flixprize challenge. ACM SIG KDD Explorations News letter, 9(2):75–79, 2007.
[2] A. Berg, J. Deng, and L. Fei-Fei. Large scale visual recognition challenge 2010. www.imagenet.org/challenges. 2010.
…
致謝：https://blog.csdn.net/qianqing13579/article/details/71381016?locationNum=15&fps=1
