Abstract | ||
---|---|---|
Metacognitive architectures provide one solution to the brittleness problem for agents operating in complex, changing environments. The Metacognitive Loop, in which a system notes an anomaly, assesses the problem and guides a solution, is one form of such an architecture. This paper extends prior work on implementing the note phase of this process in symbolic planning domains using the A-distance. This extension uses a growing neural gas algorithm to construct a network which represents various normal and anomalous states. Testing shows that this technique allows for improved detection of anomalies in the note phase as well as categorization of anomalies by severity and type in the assess phase. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICTAI.2013.35 | ICTAI |
Keywords | Field | DocType |
symbolic planning,metacognitive architecture,neural gas,neural gas algorithm,metacognitive loop,symbolic anomaly detection,improved detection,note phase,anomalous state,brittleness problem,neural nets | Anomaly detection,Categorization,Computer science,Artificial intelligence,Artificial neural network,Neural gas,Machine learning | Conference |
ISSN | Citations | PageRank |
1082-3409 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matthew Paisner | 1 | 2 | 1.36 |
Michael T. Cox | 2 | 882 | 72.17 |
Don Perlis | 3 | 14 | 5.72 |