- Title Pages
- Foreword
- 1 Metareasoning: An Introduction
- 2 There’s No “Me” in “Meta”—Or Is There?
- 3 Metareasoning and Bounded Rationality
- 4 Learning Expertise with Bounded Rationality and Self-Awareness
- 5 Controlling Deliberation in Coordinators
- 6 Goal-Directed Metacontrol for Integrated Procedure Learning
- 7 Metareasoning for Multispectral Satellite Image Interpretation
- 8 Metareasoning as a Formal Computational Problem
- 9 Metareasoning, Monitoring, and Self-Explanation
- 10 Metareasoning for Self-Adaptation in Intelligent Agents
- 11 Using Introspective Reasoning to Improve CBR System Performance
- 12 The Metacognitive Loop and Reasoning about Anomalies
- 13 Coordinating Agents’ Metalevel Control
- 14 The Role of Metareasoning in Achieving Effective Multiagent Coordination
- 15 Distributed Metamanagement for Self-Protection and Self-Explanation
- 16 Weighted Prediction Divergence for Metareasoning
- 17 Metareasoning as an Integral Part of Commonsense and Autocognitive Reasoning
- 18 Robotic Models of Self
- 19 Anthropomorphic Self-Models for Metareasoning Agents
- 20 Varieties of Metacognition in Natural and Artificial Systems
- Contributors
- Index
The Metacognitive Loop and Reasoning about Anomalies
The Metacognitive Loop and Reasoning about Anomalies
- Chapter:
- (p.183) 12 The Metacognitive Loop and Reasoning about Anomalies
- Source:
- Metareasoning
- Author(s):
Matthew D. Schmill
Michael L. Anderson
Scott Fults
Darsana Josyula
Tim Oates
Don Perlis
Hamid Shahri
Shomir Wilson
Dean Wright
- Publisher:
- The MIT Press
This chapter describes an architecture for generalized metacognition—called the metacognitive loop (MCL)—aimed at making artificial intelligence (AI) systems more robust. The key to this enhancement is to characterize a system by its expectations each time it engages in activity, to watch for violations of system expectations, and to attempt to reason in an application-general way about the violation to arrive at a diagnosis and plan for recovery.
Keywords: metacognition, artificial intelligence, cognitive systems, metacognitive loop
MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
Please, subscribe or login to access full text content.
If you think you should have access to this title, please contact your librarian.
To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.
- Title Pages
- Foreword
- 1 Metareasoning: An Introduction
- 2 There’s No “Me” in “Meta”—Or Is There?
- 3 Metareasoning and Bounded Rationality
- 4 Learning Expertise with Bounded Rationality and Self-Awareness
- 5 Controlling Deliberation in Coordinators
- 6 Goal-Directed Metacontrol for Integrated Procedure Learning
- 7 Metareasoning for Multispectral Satellite Image Interpretation
- 8 Metareasoning as a Formal Computational Problem
- 9 Metareasoning, Monitoring, and Self-Explanation
- 10 Metareasoning for Self-Adaptation in Intelligent Agents
- 11 Using Introspective Reasoning to Improve CBR System Performance
- 12 The Metacognitive Loop and Reasoning about Anomalies
- 13 Coordinating Agents’ Metalevel Control
- 14 The Role of Metareasoning in Achieving Effective Multiagent Coordination
- 15 Distributed Metamanagement for Self-Protection and Self-Explanation
- 16 Weighted Prediction Divergence for Metareasoning
- 17 Metareasoning as an Integral Part of Commonsense and Autocognitive Reasoning
- 18 Robotic Models of Self
- 19 Anthropomorphic Self-Models for Metareasoning Agents
- 20 Varieties of Metacognition in Natural and Artificial Systems
- Contributors
- Index