Course syllabus: Generative deep learning
From Research management course
=Classes
- 02.09 Autoregressive models (MADE, WaveNet, PicelCNN)
- 09.09 Bayesian framework. Latent variable models, EM-algorithm
- 16.09 EM-algorithm, VAE, Mean field approximation
- 23.09 Flow models (NICE, RealNVP, RevNet, i-RevNet)
- 30.09 Flow models (Glow, Flow++), Flows in VAE, Autoregressive flows (IAF)
- 07.10 Autoregressive flows (IAF, MAF, Parallel WaveNet), ELBO surgery,
- 14.10 VampPrior, Posterior collapse (PixelVAE, VLAE), Decoder weakening, IWAE
- 21.10 Vanila GAN, Vanishing gradients, mode collapse, KL vs JSD, DCGAN, Wasserstein distance
- 28.10 Wasserstein GAN, Spectral Normalization GAN, f-divergence#10 11.11 GAN evaluation, Advanced GANs (SAGAN, BigGAN, ProGAN, StyleGAN)
- 25.11 Disentanglement (InfoGAN, beta-VAE, DIP-VAE, FactorVAE)
- 09.12 Continious-in-time models (NeuralODE, FFjord), Quantized latent models (VQ-VAE, VQ-VAE-2, FQ-GAN).
Homeworks
- Autoregressive models 28.09
- Latent variable models, Flows 12.10
- Autoregressive flows, Flows in VAE 26.10
- GAN, WGAN09 11