Workshop
Metacognition in the Age of AI: Challenges and Opportunities
Ingmar Posner 路 Francesca Rossi 路 Lior Horesh 路 Steve Fleming 路 Oiwi Parker Jones 路 Rohan Paul 路 Biplav Srivastava 路 Andrea Loreggia 路 Marianna Ganapini
Mon 13 Dec, 5:45 a.m. PST
Recent progress in artificial intelligence has transformed the way we live, work, and interact. Machines are mastering complex games and are learning increasingly challenging manipulation skills. Yet where are the robot agents that work for, with, and alongside us? These recent successes rely heavily on the ability to learn at scale, often within the confines of a virtual environment. This presents significant challenges for embodied systems acting and interacting in the real world. In contrast, we require our robots and algorithms to operate robustly in real-time, to learn from a limited amount of data, to take mission and sometimes safety-critical decisions, and increasingly even to display a knack for creative problem solving. Achieving this goal will require artificial agents to be able to assess - or introspect - their own competencies and their understanding of the world. Faced with similar complexity, there are a number of cognitive mechanisms which allow humans to act and interact successfully in the real world. Our ability to assess the quality of our own thinking - that is, our capacity for metacognition - plays a central role in this. We posit that recent advances in machine learning have, for the first time, enabled the effective implementation and exploitation of similar processes in artificial intelligence. This workshop brings together experts from psychology and cognitive science with cutting-edge research in machine learning, robotics, representation learning and related disciplines, with the ambitious aim of re-assessing how models of intelligence and metacognition can be leveraged in artificial agents given the potency of the toolset now available.
Schedule
Mon 5:45 a.m. - 6:00 a.m.
|
Introduction to the Workshop on Metacognition in the Age of AI: Challenges and Opportunities
(
Live introduction from organizers
)
>
SlidesLive Video |
Ingmar Posner 路 Steve Fleming 路 Francesca Rossi 馃敆 |
Mon 6:00 a.m. - 6:30 a.m.
|
How does a brain compute confidence?
(
Invited Talk
)
>
SlidesLive Video |
Megan Peters 馃敆 |
Mon 6:30 a.m. - 7:00 a.m.
|
Credit Assignment & Meta-Learning in a Single Lifelong Trial
(
Invited Talk
)
>
SlidesLive Video |
J眉rgen Schmidhuber 馃敆 |
Mon 7:00 a.m. - 8:00 a.m.
|
Panel Discussion 1
(
Panel Discussion/Q&A
)
>
SlidesLive Video |
Megan Peters 路 J眉rgen Schmidhuber 路 Simona Ghetti 路 Nick Roy 路 Oiwi Parker Jones 路 Ingmar Posner 馃敆 |
Mon 8:00 a.m. - 8:15 a.m.
|
Coffee Break
|
馃敆 |
Mon 8:15 a.m. - 8:45 a.m.
|
Freespace Supports Metacognition for Navigation
(
Invited Talk
)
>
link
SlidesLive Video |
Susan L Epstein 馃敆 |
Mon 8:45 a.m. - 9:15 a.m.
|
Desiderata and ML Research Programme for Higher-Level Cognition
(
Invited Talk
)
>
SlidesLive Video |
Yoshua Bengio 馃敆 |
Mon 9:15 a.m. - 10:15 a.m.
|
Panel Discussion 2
(
Panel Discussion/Q&A
)
>
SlidesLive Video |
Susan L Epstein 路 Yoshua Bengio 路 Lucina Uddin 路 Rohan Paul 路 Steve Fleming 馃敆 |
Mon 10:15 a.m. - 10:25 a.m.
|
Poster/Paper Spotlights
(
1 minute / 1 slide introductions to posters
)
>
|
Ezgi Korkmaz 路 Marianna Ganapini 路 Ruiqi He 路 Rylan Schaeffer 路 Kevin O'Neill 馃敆 |
Mon 10:25 a.m. - 10:30 a.m.
|
Grab Lunch
|
馃敆 |
Mon 10:30 a.m. - 11:30 a.m.
|
Poster Session ( Poster Session ) > link | 馃敆 |
Mon 11:30 a.m. - 12:00 p.m.
|
Break
|
馃敆 |
Mon 12:00 p.m. - 12:30 p.m.
|
Performance-Optimized Neural Networks as an Explanatory Framework for Decision Confidence
(
Invited Talk
)
>
SlidesLive Video |
Taylor Webb 路 Hakwan Lau 馃敆 |
Mon 12:30 p.m. - 1:00 p.m.
|
Causal World Models
(
Invited Talk
)
>
SlidesLive Video |
Bernhard Sch枚lkopf 馃敆 |
Mon 1:00 p.m. - 2:00 p.m.
|
Panel Discussion 3
(
Panel Discussion/Q&A
)
>
SlidesLive Video |
Taylor Webb 路 Hakwan Lau 路 Bernhard Sch枚lkopf 路 Jiangying Zhou 路 Lior Horesh 路 Francesca Rossi 馃敆 |
Mon 2:00 p.m. - 2:30 p.m.
|
Closing Remarks
(
Capstone to the day, and thanks, from the organizers
)
>
SlidesLive Video |
馃敆 |
-
|
An Algorithmic Theory of Metacognition in Minds and Machines ( Poster ) > link | Rylan Schaeffer 馃敆 |
-
|
Promoting Metacognitive Learning through Systematic Reflection ( Poster ) > link | Frederic Becker 馃敆 |
-
|
Meta Dynamic Programming ( Poster ) > link | Pierluca D'Oro 馃敆 |
-
|
Non-Robust Feature Mapping in Deep Reinforcement Learning ( Poster ) > link | Ezgi Korkmaz 馃敆 |
-
|
Have I done enough planning or should I plan more? ( Poster ) > link | Ruiqi He 馃敆 |
-
|
Thinking Fast and Slow in AI: The Role of Metacognition ( Poster ) > link | Marianna Ganapini 馃敆 |
-
|
Measuring and Modeling Confidence in Human Causal Judgment ( Poster ) > link | Kevin O'Neill 馃敆 |