| Metacognition |
| Written by Carlos García | |
| Monday, 24 April 2006 | |
METACOGNITION RESOURCESThis page is intended as a minor source of metacognition material. It can be a good starting point for those interested in this field of Artificial Intelligence. WHAT IS METACOGNITION
Metacognition refers to thinking about cognition. While the normal cognition is achieved taking the real world as subject, metacognition operates on one's cognition. It involves planning, self-monitoring and self-evaluation. It has evolved from the psycology domain to be used within the computer science domain. The psychologist John H. Flavell is credited with initiating research into metacognition. Flavell (1976) describes it as follows: "Metacognition refers to one's knowledge concerning one's own cognitive processes or anything related to them, e.g., the learning-relevant properties of information or data. For example, I am engaging in metacognition if I notice that I am having more trouble learning A than B; if it strikes me that I should double check C before accepting it as fact."
An overview of human metacognition:
...and another one
(Jennifer A. Livingston, 1997):
For a selected review on
Metacognition in Computation (Michael Cox):
...and also a second one (Mike Anderson, 2005):
A description of the characteristics of metacognition: METACOGNITION FOR AGENTSOur main interest in metacognition is how intelligent agents can use it for learning and improving his own performance. Metacognitive behaviour in Adaptive Agents (Thompson, Cohen & Freeman, 1995) Perpetual Self-Aware Cognitive Agents (Cox, 2005) Incorporating Metacognitive Capabilities in Synthetic Cognition (Zachary & Le Mentec, 2000) How to make our robots conscious of their mental states (John McCarthy, 2005) ARCHITECTURESThere are some cognitive architectures out there that have some focus on metacognitional aspects: |
|
| Last Updated ( Saturday, 13 May 2006 ) |