Name
Abstract | ||
|---|---|---|
In this paper, we present an approach to transfer that involves analogical mapping of symbols across different domains. We relate this mechanism to Icarus, a theory of the human cognitive architecture. Our system can transfer skills across domains hypothesizing maps between representations, improving performance in novel domains. Unlike previous approaches to analogical transfer, our method uses an explanatory analysis that compares how well a new domain theory explains previous solutions under different mapping hypotheses. We present experimental evidence that the new mechanism improves transfer over Icarus' basic learning processes. Moreover, we argue that the same features which distinguish Icarus from other architectures support representation mapping in a natural way and operate synergistically with it. These features enable our analogy system to translate a map among concepts into a map between skills, and to support transfer even if two domains are only partially analogous. We also discuss our system's relation to other work on analogy and outline directions for future research. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1016/j.cogsys.2008.09.008 | Cognitive Systems Research |
Keywords | Field | DocType |
previous solution,basic learning process,analogy system,transfer,new mechanism,agent architectures,representation mapping,cognitive architectures,skill transfer,analogy,new domain theory,architectures support representation mapping,transfer learning,goal-driven representation mapping,analogical mapping,previous approach,different domain,different mapping hypothesis,agent architecture,domain theory,cognitive architecture | ICARUS,Cognitive science,Computer science,Skill transfer,Transfer of learning,Domain theory,Artificial intelligence,Analogy,Cognitive architecture,Machine learning,Basic learning | Journal |
Volume | Issue | ISSN |
10 | 3 | Cognitive Systems Research |
Citations | PageRank | References |
11 | 0.67 | 16 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tolga Könik | 1 | 86 | 8.21 |
| Paul O'Rorke | 2 | 116 | 64.48 |
| Dan Shapiro | 3 | 11 | 0.67 |
| Dongkyu Choi | 4 | 181 | 13.69 |
| Negin Nejati | 5 | 94 | 5.95 |
| Pat Langley | 6 | 6471 | 1307.64 |