Математические методы прогнозирования (практика, В.В. Стрижов)/Группа 574, осень 2019

Материал из MachineLearning.

(Различия между версиями)
Перейти к: навигация, поиск
(Группа)
(Группа)
Строка 5: Строка 5:
__NOTOC__
__NOTOC__
 +
 +
__NOTOC__
 +
 +
This series of seminars continues the course Bayesian model selection and investigates the theoretical aspects of model selection in various application problems.
 +
 +
Videolectures are available [https://www.youtube.com/playlist?list=PLk4h7dmY2eYH9RtoKGzxHKji0GLiBzSlZ here].
 +
 +
==== Seminar 1 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels1.pdf‎|slides]]) ====
 +
* Generative models
 +
* Applications
 +
* Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN)
 +
 +
==== Seminar 2 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels2.pdf‎|slides]]) ====
 +
* Generative vs discriminative
 +
* Latent variable models
 +
* Variational Inference
 +
* ELBO
 +
* Variational Autoencoder
 +
 +
==== Seminar 3 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels3.pdf‎|slides]]) ====
 +
* Mean field approximation
 +
* Flow models (NICE, RealNVP)
 +
 +
==== Seminar 4 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels4.pdf‎|slides]]) ====
 +
* VAE Limitations
 +
* Flows in VAE
 +
* Autoregressive flows (MAF, IAF, Parallel WaveNet)
 +
 +
==== Seminar 5 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels5.pdf‎|slides]]) ====
 +
* IWAE (lower bound, posterior, inactive units)
 +
* ELBO surgery
 +
* VampPrior
 +
 +
==== Seminar 6 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels6.pdf‎|slides]]) ====
 +
* Autoregressive decoder in VAE
 +
* Posterior collapse, decoder weakening
 +
* Disentangled representations
 +
* beta-VAE
 +
 +
== Группа ==
== Группа ==
Строка 185: Строка 225:
|-
|-
|}
|}
-
 
-
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, [[Медиа:Isachenko2019DeepGenerativeModels1.pdf‎|slides]]) ====
 
-
* Generative models
 
-
* Applications
 
-
* Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN)
 
-
 
-
==== Seminar 2 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels2.pdf‎|slides]]) ====
 
-
* Generative vs discriminative
 
-
* Latent variable models
 
-
* Variational Inference
 
-
* ELBO
 
-
* Variational Autoencoder
 
-
 
-
==== Seminar 3 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels3.pdf‎|slides]]) ====
 
-
* Mean field approximation
 
-
* Flow models (NICE, RealNVP)
 
-
 
-
==== Seminar 4 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels4.pdf‎|slides]]) ====
 
-
* VAE Limitations
 
-
* Flows in VAE
 
-
* Autoregressive flows (MAF, IAF, Parallel WaveNet)
 
-
 
-
==== Seminar 5 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels5.pdf‎|slides]]) ====
 
-
* IWAE (lower bound, posterior, inactive units)
 
-
* ELBO surgery
 
-
* VampPrior
 
-
 
-
==== Seminar 6 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels6.pdf‎|slides]]) ====
 
-
* Autoregressive decoder in VAE
 
-
* Posterior collapse, decoder weakening
 
-
* Disentangled representations
 
-
* beta-VAE
 

Версия 10:29, 12 октября 2019


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.

Videolectures are available here.

Seminar 1 (Isachenko, slides)

  • Generative models
  • Applications
  • Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN)

Seminar 2 (Isachenko, slides)

  • Generative vs discriminative
  • Latent variable models
  • Variational Inference
  • ELBO
  • Variational Autoencoder

Seminar 3 (Isachenko, slides)

  • Mean field approximation
  • Flow models (NICE, RealNVP)

Seminar 4 (Isachenko, slides)

  • VAE Limitations
  • Flows in VAE
  • Autoregressive flows (MAF, IAF, Parallel WaveNet)

Seminar 5 (Isachenko, slides)

  • IWAE (lower bound, posterior, inactive units)
  • ELBO surgery
  • VampPrior

Seminar 6 (Isachenko, slides)

  • Autoregressive decoder in VAE
  • Posterior collapse, decoder weakening
  • Disentangled representations
  • beta-VAE


Группа

5 курс

Студент Тест 1 Тест 2 Тест 3 Тест 4 Тест 5 HW 1 HW 2
Васильев Илья - - 0.59 - - -
Гадаев Тамаз Тазикоевич 0.56 0.94 0.75 - 0.88 -
Гладин Егор Леонидович - - - - - -
Грабовой Андрей Валериевич 0.63 0.31 0.67 0 - Essay
Кислинский Вадим Геннадьевич - - - - - -
Козлинский Евгений Михайлович - - - - - -
Криницкий Константин Денисович - 0.25 - - - essay
Кириллов Егор Дмитриевич - - - - - -
Рогозина Анна Андреевна - - - - - -
Плетнев Никита Вячеславович 0.82 0.25 0.67 - 0.63 Essay
Малиновский Григорий Станиславович 0.82 0.81 0.84 1 0.63 [1]
Самохина Алина Максимовна - - 0.25 1 0.75 -
Султанов Азат Русланович - - - - - -
Федосов Павел Андреевич - - - - - -
Шульгин Егор Владимирович - - 0.34 - - 0.13

6 курс

Студент HW 1 HW 2
Сайранов Данил -
Фельдман Даниил -
Никитин Филипп -
Фалахов И -
Собраков -


  • 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
Личные инструменты