.. image:: pystat.png :height: 20 :alt: Statistique :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-data-scientist .. _l-ml2a-deep-gan: Generative Adversarial Network (GAN) ++++++++++++++++++++++++++++++++++++ *(à venir)* *Lectures* * `Generative Adversarial Networks `_ : c'est le premier article paru sur le sujet * `Least Squares Generative Adversarial Networks `_ * `f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization `_ * `Fader Networks: Manipulating Images by Sliding Attributes `_ * `Partial Information Attacks on Real-world AI `_ * `Synthesizing Robust Avdersarial Examples `_ * `PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples `_ * `Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey `_ * `StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks `_ * `How Generative Adversarial Networks and its variants Work: An Overview of GAN `_ * `Synthesizing Programs for Images using Reinforced Adversarial Learning `_ * `Flipped-Adversarial AutoEncoders `_ *Exemples de code* * `generative-models `_ : programme sur une grande variété de GAN (Vanilla, Conditional, f-GAN, ...) avec :epkg:`tensorflow` et :epkg:`pytorch` * `Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch) `_