Deep learning, reinforcement learning, and world models.
Yutaka Matsuo, Yann LeCun, Maneesh Sahani, Doina Precup, David Silver, Masashi Sugiyama, Eiji Uchibe, Jun Morimoto
Author Information
Yutaka Matsuo: The University of Tokyo, Japan.
Yann LeCun: New York University, Courant Institute & Center for Data Science, United States of America; Facebook AI Research, United States of America.
Maneesh Sahani: Gatsby Computational Neuroscience Unit, University College London, United Kingdom.
Doina Precup: DeepMind, United Kingdom; McGill University, Canada.
David Silver: DeepMind, United Kingdom.
Masashi Sugiyama: RIKEN Center for Advanced Intelligence Project, Japan; The University of Tokyo, Japan.
Eiji Uchibe: Advanced Telecommunication Research International (ATR), Japan.
Jun Morimoto: Advanced Telecommunication Research International (ATR), Japan; Kyoto University, Japan. Electronic address: xmorimo@atr.jp.
Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable factors to achieve human-level or super-human AI systems. On the other hand, both DL and RL have strong connections with our brain functions and with neuroscientific findings. In this review, we summarize talks and discussions in the "Deep Learning and Reinforcement Learning" session of the symposium, International Symposium on Artificial Intelligence and Brain Science. In this session, we discussed whether we can achieve comprehensive understanding of human intelligence based on the recent advances of deep learning and reinforcement learning algorithms. Speakers contributed to provide talks about their recent studies that can be key technologies to achieve human-level intelligence.
