The autoencoder code is inspired from: http://alexadam.ca/ml/2017/05/05/keras-vae.html
For implementing some parts of GAN, we used https://github.com/roatienza/Deep-Learning-Experiments/blob/master/Experiments/Tensorflow/GAN/dcgan_mnist.py, and https://towardsdatascience.com/writing-your-first-generative-adversarial-network-with-keras-2d16fd8d4889.
[1] Martin Arjovsky, Soumith Chintala, and L ́eon Bottou.Wasserstein GAN. 2017. arXiv:1701.07875 [stat.ML].
[2] Corinna Cortes and Vladimir Vapnik. “Support-vector networks”. In:Machine Learning20.3(Sept. 1995), pp. 273–297.issn: 1573-0565.doi:10.1007/BF00994018.url:https://doi.org/10.1007/BF00994018.
[3] David Donahue and Anna Rumshisky.Adversarial Text Generation Without ReinforcementLearning. 2019. arXiv:1810.06640 [cs.CL].
[4] Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy.Explaining and Harnessing Ad-versarial Examples. 2015. arXiv:1412.6572 [stat.ML].
[5] Ian J. Goodfellow et al.Generative Adversarial Networks. 2014. arXiv:1406.2661 [stat.ML].
[6] Sepp Hochreiter and J ̈urgen Schmidhuber. “Long Short-Term Memory”. In:Neural Comput.9.8 (Nov. 1997), pp. 1735–1780.issn: 0899-7667.doi:10.1162/neco.1997.9.8.1735.url:https://doi.org/10.1162/neco.1997.9.8.1735.
[7]IMDB Dataset of 50K Movie Reviews. 2019.url:https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews.
[8]Intuitive Guide to Understanding GloVe Embeddings. 2019.url:https://towardsdatascience.com/light- on- math- ml- intuitive- guide- to- understanding- glove- embeddings-b13b4f19c010.
[9] Christopher D. Manning Jeffrey Pennington Richard Socher.GloVe: Global Vectors for WordRepresentation. 2014.url:https://nlp.stanford.edu/projects/glove/.
[10] Diederik P Kingma and Max Welling.Auto-Encoding Variational Bayes. 2014. arXiv:1312.6114 [stat.ML].18
[11] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. “ImageNet Classification with DeepConvolutional Neural Networks”. In:Advances in Neural Information Processing Systems.Ed. by F. Pereira et al. Vol. 25. Curran Associates, Inc., 2012.url:https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf.
[12] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. “Deep learning”. In:Nature521.7553(May 2015), pp. 436–444.issn: 1476-4687.doi:10.1038/nature14539.url:https://doi.org/10.1038/nature14539.
[13] Bin Liang et al. “Deep Text Classification Can be Fooled”. In:CoRRabs/1704.08006 (2017).arXiv:1704.08006.url:http://arxiv.org/abs/1704.08006.
[14] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. “” Why should i trust you?” Ex-plaining the predictions of any classifier”. In:Proceedings of the 22nd ACM SIGKDD inter-national conference on knowledge discovery and data mining. 2016, pp. 1135–1144.
[15] Tim Salimans et al.Improved Techniques for Training GANs. 2016. arXiv:1606 . 03498[cs.LG].
[16] M. Schuster and K. K. Paliwal. “Bidirectional recurrent neural networks”. In:IEEE Trans-actions on Signal Processing45.11 (1997), pp. 2673–2681.doi:10.1109/78.650093.
[17] Christian Szegedy et al. “Intriguing properties of neural networks”. In:International Confer-ence on Learning Representations.
2014.url:http://arxiv.org/abs/1312.6199.
[18] Chaowei Xiao et al. “Generating Adversarial Examples with Adversarial Networks”. In:CoRRabs/1801.02610 (2018).
arXiv:1801.02610.url:http://arxiv.org/abs/1801.02610.
[19] Wei Emma Zhang et al.Adversarial Attacks on Deep Learning Models in Natural LanguageProcessing: A Survey. 2019. arXiv:1901.06796 [cs.CL].
[20] Zhengli Zhao, Dheeru Dua, and Sameer Singh.Generating Natural Adversarial Examples.2018. arXiv:1710.11342 [cs.LG].