[1] [1] Goodfellow I J，Warde-Farley D，Mirza M，et al. Maxout networks［C］. Proceedings of the 30th International Conference on Machine Learning（ICML），2013：1319-1327.

[2] [2] Goodfellow I，Pouget-Abadie J，Mirza M，et al. Generative adversarial nets［C］. Advances in Neural Information Processing Systems，2014：2672-2680.

[3] [3] Bergstra J，Bengio Y. Random search for hyper-parameter optimization［J］. Journal of Machine Learning Research，2012，13（1）：281-305.

[4] [4] Coates A，Ng A Y. Learning feature representations with K-means［J］. Lecture Notes in Computer Science，2012，7700：561-580.

[5] [5] Dosovitskiy A，Fischer P，Springenberg J，et al. Discriminative unsupervised feature learning with exemplar convolutional neural networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2015：1-1.

[6] [6] Gregor K，Danihelka I，Graves A，et al. DRAW：A recurrent neural network for image generation［C］. Proceedings of the 32th International Conference on Machine Learning，2015，37：1462-1471.

[7] [7] Zeiler，Matthew D，Fergus Rob. Visualizing and understanding convolutional networks［C］. In Computer Vision-ECCV 2014：818-833.

[8] [8] Vincent，Pascal，Larochelle，et al. Stacked denoising autoencoders：Learning useful representations in a deep network with a local denoising criterion［J］. The Journal of Machine Learning Research，2010，11：3371-3408.

[9] [9] Ioffe，Sergey，Szegedy，et al. Batch normalization：Accelerating deep network training by reducing internal covariate shift［J］. arXiv preprint arX-iv：1502.03167，2015.

[10] [10] Freeman，William T，Jones，et al. Example-based super-resolution［J］. Computer Graphics and Applications，IEEE，2002，22（2）：56-65.

[11] [11] Junbo Zhao，Micheal Mathieu，Ross Goroshin，et al. Stacked what-where autoencoders［J］. arXiv preprint arXiv：1506.02351，2015.

[12] [12] Fisher Yu，Yinda Zhang，Shuran Song，et al. LSUN：Construction of a large-scale image dataset using deep learning with humans in the loop［J］. arXiv preprint arXiv：1506.03365，2015.

[13] [13] XU Bing，WANG Naiya，CHEN Tianqi，et al. Empirical evaluation of rectified activations in convolutional network［J］. arXiv preprint ar-Xiv：1505.00853，2015.

[14] [14] Jascha Sohl-Dickstein， Eric A Weiss， Niru Maheswaranathan， et al. Deep unsupervised learning using nonequilibrium thermo-dynamics［J］. arXiv preprint arXiv：1503.03585，2015.

[15] [15] Antti Rasmus，Harri Valpola，Mikko Honkala，et al. Semisupervised learning with ladder network［J］. arXiv preprint arXiv：1507.02672，2015.

[16] [16] Hauberg S， Freifeld O， Larsen A B L， et al. Dreaming more data： Class-dependent distributions over diffeomorphisms for learned data augmentation［J］. arXiv preprint arXiv：1510.02795，2015.

[17] [17] Hardt，Moritz，Ben Recht，et al. Train faster，generalize better：Stability of stochastic gradient descent［J］. arXiv preprint arXiv：1509.01240，2015.