jdc08161063 / realai.org

title	permalink	mathjax
Welcome to Real AI	/	true

What's New

• 2017 July 21, Marc G. Bellemare, Will Dabney, and Rémi Munos. A Distributional Perspective on Reinforcement Learning. arXiv:1707.06887. video. blog. (DeepMind; Model-Free Reinforcement Learning)
• 2017 July 19, Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, David Silver, and Daan Wierstra. Imagination-Augmented Agents for Deep Reinforcement Learning. arXiv:1707.06203. (DeepMind; Reinforcement Learning Agents)
• 2017 July 19, Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, and Peter Battaglia. Learning model-based planning from scratch. arXiv:1707.06170. (DeepMind; Planning)
• 2017 July 11, Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matthew Botvinick, Demis Hassabis, and Alexander Lerchner. SCAN: Learning Abstract Hierarchical Compositional Visual Concepts. arXiv:1707.03389. (DeepMind; Concept Learning)
• 2017 July 11, Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. Meta-Learning with Temporal Convolutions. arXiv:1707.03141. (Meta-Learning)
• 2017 July 10, Nicholas Heess, Josh Merel, and Ziyu Wang. Producing flexible behaviours in simulated environments. DeepMind Blog. (DeepMind; Robotics)
• 2017 July 5. DeepMind Goes to Alberta For First International Lab, Thanked by Justin Trudeau. Bloomberg Technology & Twitter. (DeepMind; Policies)

Table of Contents

1. Overview

   1. Progress
   2. Timing
   3. Prosaic AI
   4. Roadmaps
   5. Safety
      1. Blog: Towards Safe and Beneficial Intelligence
      2. Effective Altruism
      3. Research Groups

2. AI and Society

   1. Applications
   2. Impacts
   3. Industry
      1. Alphabet Inc.
      2. Facebook, Inc.
      3. Amazon.com, Inc.
      4. Microsoft Corporation
      5. Apple Inc.
      6. NVIDIA Corporation
      7. Tencent Holdings Limited
      8. Partnership on AI
   4. Research Groups: Conferences
      1. DeepMind: Publications
      2. Google Brain: Publications
      3. OpenAI: Publications
      4. FAIR: Publications
      5. Vector Institute
   5. Policies

3. Philosophy of Intelligence

   1. What Is Intelligence?

4. Course

5. Frontier

   1. Learning Methods
      1. Unsupervised Learning:
         • Intrinsic Motivation
           • Predictive Learning
      2. Multi-Task Learning: Continual Learning, Transfer Learning, Curriculum Learning
      3. Hierarchical Learning: Concept Learning
      4. Meta-Learning: Few-Shot Learning
   2. Learning Outcomes
      1. Symbol Grounding
      2. World Model
      3. Reasoning
      4. Attention
      5. Memory
   3. Deep Learning
      1. Network Architecture
         • Architecture Search
         • Multi-Agent Learning
         • Memory Augmented Neural Networks
      2. Learning Rules
      3. Adversarial Learning
      4. Generative Models
      5. Platforms
   4. Reinforcement Learning
      1. Safe Reinforcement Learning
      2. Agents
      3. Model-Free Algorithms
      4. Planning
      5. Intrinsic Motivation
         • Prediction
         • Exploration
         • Empowerment
      6. Auxiliary Tasks
      7. Imitation Learning
      8. General Reinforcement Learning
   5. Neuroscience
   6. Alternative Theories
   7. Experiments
      1. Vision
      2. Language: Program Induction
      3. Robotics: Autonomous Driving
      4. Games
      5. Automated Theorem Proving
   8. Theory
      1. Deep Learning Theory
   9. Implementation
      1. Deep Learning Implementations
      2. Reinforcement Learning Implemtations

6. Research