Belajar GAN

[threeal]

Repositori di sini, Report di sini.

• [x] Fundamental of GANs, here.
  • [x] Slide, here.
  • [x] GAN, GitHub, Colab.
  • [x] CGAN, GitHub, Colab.
  • [x] DCGAN, Tutorial, GitHub.
• [ ] Wasserstein GANs, here.
  • [x] Slide, here.
  • [x] WGAN, GitHub.
  • [x] WGAN-GP, GitHub.
  • [ ] WGAN-SN, GitHub.
  • [ ] WGAN-Div, GitHub.
• [ ] GAN Evaluations, here.
  • [ ] Slide, here.
• [ ] Applications of GANs, here.

Things to Know

• [ ] Generative Adversarial Networks (GAN).
  • [x] Minimax GAN (MM GAN).
  • [x] Non-Saturating GAN (NS GAN).
  • [x] Least Squares GAN (LS GAN).
  • [x] Deep Convolutional GAN (DCGAN).
  • [x] Conditional GAN (CGAN).
  • [x] Wasserstein GAN (WGAN).
  • [ ] Wasserstein GAN with Gradient Penalty (WGAN-GP).
  • [ ] Wasserstein Divergence GAN (WGAN-Div).
  • [ ] Spectral Normalization GAN (SN-GAN).
• [x] Multi-layer Perceptron (MLP).
• [ ] Deep Feed-forward Neural Networks (DNN).
• [x] Convolution Neural Networks (CNN).
• [ ] Recurrent Neural Networks (RNN).
  • [ ] Long Short Term Memory (LSTM).
• [ ] Mean Squared Error (MSE).
• [ ] Binary Cross-Entropy (BCE).
• [ ] Stochastic Gradient Descent (SGD).
• [ ] Adam Optimization.
• [ ] RMSprop.
• [ ] Nash Equilibrium.
• [ ] Earth Mover's Distance.
• [ ] Lipschitz Constraints / Continuity

Papers

• [x] Goodfellow 2014, Generative Adversarial Networks, arXiv.
• [x] Mirza 2014, Conditional Generative Adversarial Nets, arXiv.
• [x] Radford 2015, Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, arXiv.
• [ ] Arjovsky 2017, Wasserstein GAN, arXiv.
• [ ] Gulrajani 2017, Improved Training of Wasserstein GANs, arXiv.
• [ ] Miyato 2018, Spectral Normalization for Generative Adversarial Networks, Open Review.
• [ ] Wu 2018, Wasserstein Divergence for GANs, arXiv.

GAN Related Research

• [x] Heng 2017, Transfer Learning for Robot Control with Generative Adversarial Networks, PDF.
• [ ] Tobin 2017, Domain randomization for transferring deep neural networks from simulation to the real world, IEEE Xplore,

Other References

• [x] A gentle introduction to GAN here.
• [x] How do CNN work here.
• [x] A gentle introduction to ReLU here.
• [x] Neural networks representation here.
• [x] Convolution neural networks here.
• [x] Introduction to RNN here.
• [x] How Back-Propragation in ANN work here.
• [ ] Gentle Introduction to Adam Optimization here.
• [x] A Gentle Introduction to GAN Loss Functions here.
• [ ] How to choose Loss Functions in Neural Networks here.
• [x] How to implement Wasserstein Loss for GAN here.
• [ ] Understanding RMSprop here.

[threeal]

Moved here