1:32:16

AI Alignment problem [in Russian]

1:30:27

Дискуссионный семинар о диффузных моделях

1:18:01

Topological data analysis and machine learning [in Russian]

1:22:07

Image Manipulation by Diffusion Models [in Russian]

1:09:29

Self-supervised Pre-training with Masked Image Modeling [in Russian]

1:22:06

Star-Shaped Denoising Diffusion Probabilistic Models [in Russian]

1:14:33

Monolingual and Cross-lingual Text Detoxification [in Russian]

59:59

SketchBoost: быстрый бустинг для multiclass/multilabel классификации и multitask регрессии

1:29:59

Finemap-MiXeR: A variational Bayesian approach for genetic finemapping

1:24:04

Все дело в языке, а он ― меняется. И поэтому...

1:27:18

From GPT-3 to ChatGPT: Training Language Models on Instructions and Human Feedback [in Russian]

1:25:26

Domain Adaptation of GANs [in Russian]

1:31:00

Diffusion Models in Latent Space [in Russian]

1:19:29

Discovering Faster Matrix Multiplication Algorithms with Reinforcement Learning [in Russian]

1:50:20

Квантовая механика

1:40:04

Станислав Дробышевский: вопросно-ответная сессия

1:20:41

Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes [in Russian]

1:29:17

Overview of Controllable Generation of Text and Images [in Russian]

1:30:57

Diffusion Models: Discussion Seminar, Part 2 [in Russian]

1:13:08

Diffusion Models: Discussion Seminar, Part 1 [in Russian]

1:04:44

Object-Centric Representations with Slot Attention for Visual Tasks [in Russian]

1:36:07

Neural Optimal Transport [in Russian]

1:21:40

Digital Pre-Distortion [in Russian]

1:40:56

Минимизация энергии в моделях Изинга с помощью нейронных сетей

1:19:06

Novel View Synthesis [in Russian]

42:52

MLP for CV and NLP problems [in Russian]

1:11:14

Autoformer and Autoregressive Denoising Diffusion Models for Time Series Forecasting [in Russian]

1:30:14

Mathematics of Multi-Antenna Transmission in 5G networks [in Russian]

1:30:00

Диффузионные модели, восстановление изображений через обратные линейные задачи

1:22:26

Random Matrix Theory approach to Deep Learning Optimisation and Generalisation [in English]

1:39:06

Свободная энергия и интеллект

1:38:57

Formalism of Quantum Mechanics From the Point of View of Machine Learning [in Russian]

1:09:24

Resolution-Robust Large Mask Inpainting with Fourier Convolutions [in Russian]

2:00:09

From Classical Statistics to Modern Deep Learning [in Russian]

59:27

Controlling GANs Latent Space [in Russian]

1:24:50

Highly Accurate Protein Structure Prediction with AlphaFold [in English]

1:19:44

The Machine Learning of Time and Dynamics … with an Outlook towards the Sciences [in English]

1:31:40

Diffusion Models, part 3 [in Russian]

1:26:54

Diffusion Models, part 2 [in Russian]

1:40:31

Diffusion Models, part 1 [in Russian]

1:35:42

Large-Scale Wasserstein Gradient Flows [in Russian]

1:29:12

Neural Program Synthesis, part 2 [in Russian]

1:21:29

Neural Program Synthesis, part 1 [in Russian]

54:57

Imitation Learning from Observations [in Russian]

1:47:42

What Are Bayesian Neural Network Posteriors Really Like? [in Russian]

1:49:51

Audio Synthesis and Bandwidth Extension [in Russian]

1:21:51

Learning Differential Equations that are easy to solve [in Russian]

1:34:40

Tensor Programs, part 2 [in Russian]

1:19:36

Continual Learning in Neural Networks: on Catastrophic Forgetting and Beyond [in Russian]

1:31:29

Случайные матрицы: теория и приложения

1:18:47

Wasserstein-2 Generative Networks [in Russian]

1:22:00

Differentiation Through Solutions to Optimization Problems [in Russian]

1:57:59

Double Descent, Flat Minima, and SGD [in Russian]

1:56:14

Deep Learning for Source Code: Handling Syntactic Structure and Identifiers

1:25:54

General Probabilistic Surface Optimization [in English]

1:19:56

Владимир Сурдин: сессия вопросов и ответов по астрономии

1:45:52

Infinitely Wide Nets [in English]

1:42:59

On Power Laws in Deep Ensembles [in Russian]

1:38:48

Generalizations of Gumbel-Softmax Trick [in Russian]

1:20:13

Quadrature-Based Random Features and Applications [in Russian]

1:20:31

Bayesian Sparsification Methods for Deep Сomplex-Valued Networks [in Russian]

1:22:36

Planning in Deep Reinforcement Learning [in Russian]

1:43:23

Training of Binary Neural Networks [in Russian]

1:08:45

Contrastive Self-Supervised Learning for Image Representations [in Russian]

49:25

Neural Stochastic Differential Equations, part 2 [in Russian]

1:31:19

BERT: Model, Analysis and Modifications, part 2 [in Russian]

1:29:07

BERT: Model, Analysis and Modifications, part 1 [in Russian]

1:28:39

Hyperbolic Deep Learning [in Russian]

1:09:49

Quantization of Neural Networks [in Russian]

1:02:34

Uncertainty in Structured Prediction

1:20:28

Neural Program Synthesis

1:28:13

Model calibration

1:31:32

The State of Ensembling (and Uncertainty)

1:10:00

Scalable Bayesian Inference in Low-Dimensional Subspaces

1:28:15

Mathematical Models of the Genetic Architecture in Complex Human Disorders

1:03:22

Implicit λ-Jeffreys Autoencoders: Taking the Best of Both Worlds

1:09:29

Reverse KL-Divergence training of Prior Networks

1:20:05

Why do neural nets learn and generalize?

1:23:47

On Mutual Information Estimation

1:30:52

Invariant Risk Minimization

46:44

Deep Equilibrium Models

7:58

[DeepBayes2019]: Day 1, Opening remarks

1:48

[DeepBayes2019]: Day 6, Closing remarks

21:17

[DeepBayes2019]: Day 1, Practical session 2. Bayesian reasoning

1:08:47

[DeepBayes2019]: Day 1, Lecture 1. Introduction to Bayesian methods

46:27

[DeepBayes2019]: Day 6, Lecture 4. Loss surfaces

1:19:54

[DeepBayes2019]: Day 6, Keynote Lecture 3. Uncertainty estimation in supervised learning

5:52

[DeepBayes2019]: Day 6, Practical session 2. Sparsification of deep neural networks

1:14:24

[DeepBayes2019]: Day 6, Lecture 1. Bayesian neural networks

1:27:20

[DeepBayes2019]: Day 5, Lecture 4. Variational inference with implicit and semi-implicit models

14:01

[DeepBayes2019]: Day 5, Sponsor talk

1:00:45

[DeepBayes2019]: Day 5, Lecture 3. Langevin dynamics for sampling and global optimization

14:09

[DeepBayes2019]: Day 5, Practical session 2. Markov Chain Monte Carlo

1:25:57

[DeepBayes2019]: Day 5, Lecture 1. Markov Chain Monte Carlo

0:56

[DeepBayes2019]: Day 4, Practical session 5. Adaptive skip-gram model

1:03:10

[DeepBayes2019]: Day 4, Keynote Lecture 4. Adaptive skip-gram model

1:34:46

[DeepBayes2019]: Day 4, Keynote Lecture 3. Deep Gaussian processes

1:33:46

[DeepBayes2019]: Day 4, Practical session 2. Gaussian processes and Bayesian optimization

1:31:09

[DeepBayes2019]: Day 4, Lecture 1. Gaussian processes and Bayesian optimization

22:12

[DeepBayes2019]: Day 3, Practical session 4. Normalizing flows