參考文獻

[1] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.

[2] Le Quoc V. A Tutorial on Deep Learning Part 1: Nonlinear Classifiers and The Back-propagation Algorithm[EB/OL]. 2015. https://cs.stanford.edu/～quocle/tutorial1. pdf.

[3] Le Quoc V. A Tutorial on Deep Learning Part 2: Autoencoders, Convolutional Neural Networks and Recurrent Neural Networks[EB/OL]. 2015. https://cs.stanford.edu/～quocle/tutorial2. pdf.

[4] denoising autoencoder[EB/OL]. http://deeplearning. net/tutorial/dA. html.

[5] Bengio Y, Lamblin P, Popovici D, et al. Greedy Layer-wise Training of Deep Networks[C]//International Conference on Neural Information Processing Systems. Cambridge: The MIT Press, 2006: 153-160.

[6] Rumelhart D E, Hinton G E, Williams R J. Learning Internal Representation by Back-propagation of Errors[J]. Nature, 1986, 323(323): 533-536.

[7] Dean J. Large-Scale Deep Learning for Building Intelligent Computer Systems[C]//ACM International Conference on Web Search and Data Mining. ACM, 2016: 1-1.

[8] Chan W, Jaitly N, Le Quoc V, et al. Listen, Attend and Spell[J]. Computer Science, 2015.

[9] Graves A, Mohamed A, Hinton G. Speech Recognition with Deep Recurrent Neural Networks[C]. ICASSP 2013, 38(2003): 6645-6649.

[10] Zhang S, Liu C, Jiang H, et al. Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency[J]. Computer Science, 2015.

[11] 李航．統計學習方法[M]．北京：清華大學出版社，2012.

[12] 同濟大學數學教研組．高等數學（上）（下）[M]．北京：高等教育出版社，1996.

[13] 同濟大學應用數學系．線性代數[M]. 4版．北京：高等教育出版社，2003.

[14] Norman P Jouppi, et al. In-Datacenter Performance Analysis of a Tensor Processing Unit[C]. 44th International Symposium on Computer Architecture(ISCA), Toronto, Canada, June 26, 2017.

[15] Uijlings J, Sande K, Gevers T, et al. Selective Search for Object Recognition[J]. International Journal of Computer Vision, 2013, 104(2): 154-171.