Difference between revisions of "Course syllabus: Generative deep learning"

From Research management course
Jump to: navigation, search
(Created page with "===Classes== # 02.09 Autoregressive models (MADE, WaveNet, PicelCNN) # 09.09 Bayesian framework. Latent variable models, EM-algorithm # 16.09 EM-algorithm, VAE, Mean field app...")
 
 
(One intermediate revision by one other user not shown)
Line 1: Line 1:
===Classes==
+
{{#seo:
 +
|title=Generative Deep Learning - course syllabus
 +
|titlemode=replace
 +
|keywords=Generative Deep Learning
 +
|description=The course Generative Deep Learning is devoted to Autoregressive models, the Bayesian framework, latent variable models, and the EM algorithm.
 +
}}
 +
==Classes==
 
# 02.09 Autoregressive models (MADE, WaveNet, PicelCNN)
 
# 02.09 Autoregressive models (MADE, WaveNet, PicelCNN)
 
# 09.09 Bayesian framework. Latent variable models, EM-algorithm
 
# 09.09 Bayesian framework. Latent variable models, EM-algorithm
Line 12: Line 18:
 
# 09.12 Continious-in-time models (NeuralODE, FFjord), Quantized latent models (VQ-VAE, VQ-VAE-2, FQ-GAN).  
 
# 09.12 Continious-in-time models (NeuralODE, FFjord), Quantized latent models (VQ-VAE, VQ-VAE-2, FQ-GAN).  
  
===Homeworks===
+
==Homeworks==
 
# Autoregressive models 28.09
 
# Autoregressive models 28.09
 
# Latent variable models, Flows 12.10
 
# Latent variable models, Flows 12.10
 
# Autoregressive flows, Flows in VAE 26.10
 
# Autoregressive flows, Flows in VAE 26.10
 
# GAN, WGAN09 11
 
# GAN, WGAN09 11

Latest revision as of 23:50, 13 February 2024

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