Математические методы прогнозирования (практика, В.В. Стрижов)/Группа 574, осень 2019
Материал из MachineLearning.
Short link bit.ly/IS_B2
This series of seminars continues the course Bayesian model selection and investigates the theoretical aspects of model selection in various application problems.
- Seminar 1 (Isachenko, slides)
- Generative models
- Applications
- Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN)
- ELBO
- Seminar 2 (Isachenko)
- Analytic methods of approximation
- Statistic sum approximation
- Generative versus discriminative
- Seminar 3 (Isachenko)
- Inference methods of approximation
- Zoo of variational autoencoders and practical examples
- Seminar 4 (Isachenko)
- Generative adversarial networks
- Seminar 5 (Bakhteev)
- Methods of model selection
- Generalization theorem
- Seminar 6 (Bakhteev)
- Complexity theorems
- Seminar 7 (Grabovoy?)
- Mixture of experts
- Priors on the mixture
- Privileged learning and distilling
- Seminar 8 (Aduenko?)
- Theorem of number of experts
- Seminar 9 (Vladimirova?)
- Prior propagation for deep learning networks
- Seminar 10
- Directional Bayesian statistics
- Seminar 11
- Bayesian structure learning
- Seminar 12
- Probabilistic metric space construction
- Seminar 13
- Informative prior
- Seminar 14
- Bayesian programming
- Informative prior with applications