AAAI 2020 Keynotes Turing Award Winners Event - Geoff Hinton, Yann Le Cunn, Yoshua Bengio logo

AAAI 2020 Keynotes Turing Award Winners Event - Geoff Hinton, Yann Le Cunn, Yoshua Bengio

Feb 10, 2020
Highlighted Topics: - Stacked Capsule Autoencoders by Geoffrey Hinton - Self-Supervised Learning by Yann LeCun - Deep Learning for System 2 Processing by Yoshua Bengio - Panel Discussion

02:52 Talk: Stacked Capsule Autoencoders by Geoffrey Hinton 03:09 Two approaches to object recognition 03:53 Problems with CNNs: Dealing with viewpoint changes 04:42 Equivariance vs Invariance 05:25 Problems with CNNs 10:04 Computer vision as inverse computer graphics 11:55 Capsules 2019: Stacked Capsule Auto-Encoders 13:21 What is a capsule? 14:58 Capturing intrinsic geometry 15:37 The generative model of a capsule auto-encoder 20:28 The inference problem: Inferring wholes from parts 21:44 A multi-level capsule auto-encoder 22:30 How the set transformer is trained 23:14 Standard convolutional neural network for refining word representations based on their context 23:41 How transformers work 24:43 Some difficult examples of MNIST digits 25:20 Modelling the parts of MNIST digits 27:03 How some of the individual part capsules contribute to the reconstructions 28:37 Unsupervised clustering of MNIST digits using stacked capsule autoencoders 31:25 The outer loop of vision 31:36 Dealing with real 3-D images 32:51 Conclusion 36:04 Talk: Self-Supervised Learning by Yann LeCun 36:25 What is Deep Learning? 38:37 Supervised Learning works but requires many labeled samples 39:25 Supervised DL works amazingly well, when you have data 40:05 Supervised Symbol Manipulation 41:50 Deep Learning Saves Lives 43:40 Reinforcement Learning: works great for games and simulations. 45:12 Three challenges for Deep Learning 47:39 How do humans and animals learn so quickly? 47:43 Babies learn how the world works by observation 48:43 Early Conceptual Acquisition in Infants [from Emmanuel Dupoux] 49:33 Prediction is the essence of Intelligence 50:28 Self-Supervised Learning = Filling in the Blanks 50:53 Natural Language Processing: works great! 51:55 Self-Supervised Learning for Video Prediction 52:09 The world is stochastic 52:43 Solution: latent variable energy-based models 53:55 Self-supervised Adversarial Learning for Video Prediction 54:12 Three Types of Learning 55:30 How Much Information is the Machine Given during Learning? 55:54 The Next Al Revolution 56:23 Energy-Based Models 56:32 Seven Strategies to Shape the Energy Function 57:02 Denoising AE: discrete 58:44 Contrastive Embedding 1:00:39 MoCo on ImageNet 1:00:52 Latent-Variable EBM for inference & multimodal prediction 1:02:07 Learning a (stochastic) Forward Model for Autonomous Driving 1:02:26 A Forward Model of the World 1:04:42 Overhead camera on highway. Vehicles are tracked 1:05:00 Video Prediction: inference 1:05:15 Video Prediction: training 1:05:30 Actual, Deterministic, VAE+Dropout Predictor/encoder 1:05:57 Adding an Uncertainty Cost (doesn't work without it) 1:06:01 Driving an Invisible Car in "Real" Traffic 1:06:51 Conclusions 1:09:37 Talk: Deep Learning for System 2 Processing by Yoshua Bengio 1:10:10 No-Free-Lunch Theorem, Inductive Biases Human-Level AI 1:15:03 Missing to Extend Deep Learning to Reach Human-Level AI 1:16:48 Hypotheses for Conscious Processing by Agents, Systematic Generalization 1:22:02 Dealing with Changes in Distribution 1:25:13 Contrast with the Symbolic AI Program 1:28:07 System 2 Basics: Attention and Conscious Processing 1:28:19 Core Ingredient for Conscious Processing: Attention 1:29:16 From Attention to Indirection 1:30:35 From Attention to Consciousness 1:31:59 Why a Consciousness Bottleneck? 1:33:07 Meta-Learning: End-to-End OOD Generalization, Sparse Change Prior 1:33:21 What Causes Changes in Distribution? 1:34:56 Meta-Learning Knowledge Representation for Good OOD Performance 1:35:14 Example: Discovering Cause and Effect 1:36:49 Operating on Sets of Pointable Objects with Dynamically Recombined 1:37:36 RIMS: Modularize Computation and Operate on Sets of Named and Typed Objects 1:39:42 Results with Recurrent Independent Mechanisms 1:40:17 Hypotheses for Conscious Processing by Agents, Systematic Generalization 1:40:46 Conclusions 1:41:06 Panel Discussion 1:41:59 Connection between Neural Networks as a Computer Science and a Machine Learning Concept - Natural Competition 1:45:35 Idea of Differentiation: Representation and Listening 1:49:36 Alternate to Gradient Based Learning 1:51:04 What is the role of university when Facebook, Google can manage these enormous projects 1:53:50 What do you think students to read? 1:54:50 Mechanisms for Human Level AI 1:57:59 Where do new ideas come from? How do you decide which one works out? 1:59:54 How should I proceed when people writes me reviews and doesn't like my research? 2:01:53 Publications effect on the field 2:05:36 Can we code during AI doing science 2:06:52 What is not General Intelligence, how to measure? and Neural Architecture 2:08:44 Disagreements