Lecture schedule
Seminars are held every week on Tuesday at 16.15 - 18.00 Delta (Narva mnt 18) - 1022 (starting from 11.02).
Please, choose a lesson that you will moderate and homework/test for which you will prepare here.
Week 1, Feb 11: Introduction and background (Mikhail: slides)
Week 2, Feb 18: Autoregressive Models, part 1 (Andreas)
- HW1:P1 Maximum Likelihood Estimation and KL Divergence
- HW1:P2 Logistic Regression and Naive Bayes
Week 3, Feb 25: Autoregressive Models, part 2 (Youssef: slides)
- HW1:P3 Conditional Independence and Parameterization
Week 4, Mar 3: Variational Autoencoders, part 1 (Novin: slides)
- HW1:P4 Autoregressive Models
- HW1:P5 Monte Carlo Integration
Week 5, Mar 10: Variational Autoencoders, part 2 (Tarun)
- HW2:P1 Implementing the Variational Autoencoder
Week 6, Mar 17: Normalizing Flow Models, part 1 (Egert: slides, recording)
- HW2:P2 Implementing the Mixture of Gaussians VAE
Week 7, Mar 24: Normalizing Flow Models, part 2 (Dima: slides, recording)
- HW2:P3 Implementing the Importance Weighted Autoencoder
Week 8, Mar 31: Generative Adversarial Networks, part 1 (Markus: slides, recording)
- HW2:P4 Implementing the Semi-Supervised VAE
Week 9, Apr 7: Generative Adversarial Networks, part 2 (Mikhail: slides, recording)
- HW3:P1 Generative adversarial networks
Week 10, Apr 14: Energy-based Models (Viacheslav: slides, recording)
- HW3:P2 Divergence minimization
Week 11, Apr 21: Combining Generative Model Variants (Mohammad: recording)
- HW3:P3 Conditional GAN with projection discriminator
Week 12, Apr 28: Evaluation of Generative Models (Novin, Mikhail: slides, recording)
- HW3:P4:E1-4 Wasserstein GAN
Week 13, May 5: GAIL: Generative Adversarial Imitation Learning (Andre: slides, recording)
- HW3:P4:E5 Implement Wasserstein GAN
Week 14, May 12: Discreteness in Latent Variable Modeling (Mikhail)
- HW3:P5 Noise contrastive estimation