DocumentCode
1145657
Title
Companion Cognitive Systems: Design Goals and Lessons Learned So Far
Author
Forbus, Kenneth D. ; Klenk, Matthew ; Hinrichs, Thomas
Author_Institution
Northwestern Univ., Evanston, IL, USA
Volume
24
Issue
4
fYear
2009
Firstpage
36
Lastpage
46
Abstract
The companion cognitive architecture supports experiments in achieving human-level intelligence. This article describes seven key design goals of companions, relating them to properties of human reasoning and learning, and to engineering concerns raised by attempting to build large-scale cognitive systems. We summarize our experiences with companions in two domains: test taking and game playing.
Keywords
cognitive systems; human factors; learning (artificial intelligence); software architecture; companion cognitive architecture; companion cognitive systems; human reasoning; human-level intelligence; learning; Engines; Ethics; Explosions; Greedy algorithms; Humans; Polynomials; Predictive models; Psychology; Solids; Water heating; Analogy; Cognitive Architecture; cognitive modeling; game-playing; learning;
fLanguage
English
Journal_Title
Intelligent Systems, IEEE
Publisher
ieee
ISSN
1541-1672
Type
jour
DOI
10.1109/MIS.2009.71
Filename
5172888
Link To Document