📝 Add ref[GAN]

ch07_生成对抗网络(GAN)/ref.bib

@@ -11,6 +11,19 @@
   pages={271--279},
   year={2016}
 }
+@article{radford2015unsupervised,
+  title={Unsupervised representation learning with deep convolutional generative adversarial networks},
+  author={Radford, Alec and Metz, Luke and Chintala, Soumith},
+  journal={arXiv preprint arXiv:1511.06434},
+  year={2015}
+}
+@inproceedings{long2015fully,
+  title={Fully convolutional networks for semantic segmentation},
+  author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={3431--3440},
+  year={2015}
+}
 @article{choi2017stargan,
   title={Stargan: Unified generative adversarial networks for multi-domain image-to-image translation},
   author={Choi, Yunjey and Choi, Minje and Kim, Munyoung and Ha, Jung-Woo and Kim, Sunghun and Choo, Jaegul},

ch07_生成对抗网络(GAN)/第七章_生成对抗网络(GAN).md

@@ -113,7 +113,9 @@ Instance Norm比Batch Norm的效果要更好。
 GAN只适用于连续型数据的生成，对于离散型数据效果不佳，因此假如NLP方法直接应用的是character-wise的方案，Gradient based的GAN是无法将梯度Back propagation（BP）给生成网络的，因此从训练结果上看，GAN中G的表现长期被D压着打。
 ## 7.10 Reference
 ### DCGAN部分：
-
+* Radford, A., Metz, L., & Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434.
+* Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431-3440).
+* [可视化卷积操作](https://github.com/vdumoulin/conv_arithmetic)
 ### WGAN部分：
 * Arjovsky, M., & Bottou, L. (2017). Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862.
 * Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875.