Course syllabus: Generative deep learning

From Research management course
Jump to: navigation, search

Classes

  1. 02.09 Autoregressive models (MADE, WaveNet, PicelCNN)
  2. 09.09 Bayesian framework. Latent variable models, EM-algorithm
  3. 16.09 EM-algorithm, VAE, Mean field approximation
  4. 23.09 Flow models (NICE, RealNVP, RevNet, i-RevNet)
  5. 30.09 Flow models (Glow, Flow++), Flows in VAE, Autoregressive flows (IAF)
  6. 07.10 Autoregressive flows (IAF, MAF, Parallel WaveNet), ELBO surgery,
  7. 14.10 VampPrior, Posterior collapse (PixelVAE, VLAE), Decoder weakening, IWAE
  8. 21.10 Vanila GAN, Vanishing gradients, mode collapse, KL vs JSD, DCGAN, Wasserstein distance
  9. 28.10 Wasserstein GAN, Spectral Normalization GAN, f-divergence#10 11.11 GAN evaluation, Advanced GANs (SAGAN, BigGAN, ProGAN, StyleGAN)
  10. 25.11 Disentanglement (InfoGAN, beta-VAE, DIP-VAE, FactorVAE)
  11. 09.12 Continious-in-time models (NeuralODE, FFjord), Quantized latent models (VQ-VAE, VQ-VAE-2, FQ-GAN).

Homeworks

  1. Autoregressive models 28.09
  2. Latent variable models, Flows 12.10
  3. Autoregressive flows, Flows in VAE 26.10
  4. GAN, WGAN09 11
Retrieved from ‘https://m1p.org/index.php?title=Course_syllabus:_Generative_deep_learning&oldid=1415’