20161015第十期



關於深度學習網絡的兩個問題


作者:郭宗杰 C.-C. Jay Kuo  
譯者:趙學信 

本文預覽

作者簡介

郭宗杰為南加州大學電機、資訊與數學系教授,現任該校多媒體通訊實驗室主任。其研究領域包括多媒體資料壓縮、傳播與網絡技術、視覺大數據分析、資訊鑑識與安全,是多媒體技術領域的領導人。

譯者簡介

趙學信為網路工程師。兼事翻譯、寫作。

延伸閱讀

▼"LeNet-5, convolutional neural networks" 這是深度學習學者勒 丘的網頁,其中有LeNet-5 的許多資料。 http://yann.lecun.com/exdb/lenet/

▼要順利閱讀本文,可以先閱讀捲積式類神經網絡的簡介。網路上 有許多資源,底下是兩個例子:
http://cs231n.github.io/convolutional-networks/#conv http://deeplearning4j.org/convolutionalnets.html

▼本文作者在南加大主持的MediaComm 實驗室網站 http://mcl.usc.edu

參考資料

[1] Y. LeCun, Y. Bengio, and G. E. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.

[2] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.

[3] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2012, pp. 1097–1105.

[4] A. Coates, H. Lee, and A. Y. Ng, “An analysis of single-layer networks in unsupervised feature learning,” in Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS). JMLR:W&CP 15, 2011, vol. 15, pp. 215–223.

[5] C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. J. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” 2013. [Online]. Available: http://arxiv.org/abs/1312.6199