Arvutiteaduse instituut
  1. Kursused
  2. 2019/20 kevad
  3. Special Course in Machine Learning: Deep Generative Models (MTAT.03.317)
EN
Logi sisse

Special Course in Machine Learning: Deep Generative Models 2019/20 kevad

  • Main
  • Schedule
  • Homeworks
  • Links

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

Week 15, May 19: reserved for general discussions

Week 16, May 26: reserved for occasional skip

  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Tartu Ülikooli arvutiteaduse instituudi kursuste läbiviimist toetavad järgmised programmid:
euroopa sotsiaalfondi logo