29:17

A Case Against Generative Models in RL? - Shakir Mohamed

30:27

Possible formalizations of Representation Learning - Olivier Bousquet

28:09

Deep Exploration via Randomized Value Functions - Ian Osband

24:36

Symbolic representation learning - Marta Garnelo

29:26

Unsupervised Disentanglement or How to Transfer Skills and Imagine Things - Irina Higgins

42:28

Searching for the Principles of Reasoning and Intelligence - Shakir Mohamed

34:36

Posterior sampling for reinforcement learning: worst case regret bounds - Shipra Agrawal

34:46

Backtracking model for Efficient Reinforcement Learning - Anirudh Goyal

37:15

Planning in reinforcement learning with learned models in Dyna - Martha White

38:49

Noisy natural gradient as variational inference - Roger Grosse

03:28

Generative Models in Reinforcement Learning - Opening Remarks - Stefano Ermon

37:37

Neural decision making in human and machine vision - Matthias Bethge

30:03

Supervised Learning of Rules for Unsupervised Representation Learning - Jascha Sohl-Dickstein

38:06

Learning Representations for Hyperparameter Transfer Learning - Cédric Archambeau

37:57

Inference, relevance and statistical structure - Harri Valpola

18:36

Goals and Principles of Representation Learning - Ferenc Huszár

01:03:17

Counterfactual Explanations and EU's General Data Protection Regulation - Sandra Wachter

07:06

Dynamic Time of Flight (CVPR 2017 paper)

43:24

Innate Knowledge - Chris Watkins

39:13

Unsupervised Learning for RL - Max Jaderberg

30:43

Towards Safe Learning during Closed-loop Control - Melanie Zeilinger

23:38

Unifying Multi-Step Reinforcement Learning Methods through Matrix Splittings - Pierre-Luc Bacon

27:18

When the patient in front of you is the data source - Aldo Faisal

25:09

Goal-Driven Dynamics Learning for Model-Based RL - Roberto Calandra

29:34

Learning flexible models of nonlinear dynamical systems - Thomas Schön

43:33

On Possible Relationships between Episodic Memory, Semantic Memory and Perception - Volker Tresp

25:35

Generator-aware Discriminators & Discriminator-aware Generators - David Duvenaud

57:24

Data Science in the Wolfram Language - Sebastian Bodenstein

54:19

Probabilistic Deep Learning - Stock Take 2017 - Sebastian Nowozin

32:07

Connecting GANs, Actor-Critic Methods and Multilevel Optimization - David Pfau

28:39

On Generative Adversarial Networks and Density Estimation - Fernando Perez-Cruz

32:35

Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play - Arthur Szlam

27:27

Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks - Emily Denton

31:07

Generative Density Estimation: Convexity and Boosting - Olivier Bousquet

30:33

Two-Sample Tests, Integral Probability Metrics, and GAN Objective - Dougal J. Sutherland

11:08

DALI 2017 - Workshop - Theory of Generative Adversarial Networks - Introduction

03:24

f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization (NIPS 2016)