Abstract | ||
---|---|---|
Quite often, heuristics and common sense suggest directions for improving well-known learning algo- rithms. However it seems not an easy task to verify that the modifications are indeed helpful. This is made more complicated through various addi- tional influences inherent in different application do- mains. In order to obtain a faithful impression of phe- nomena that are intrinsic to the algorithms, the role of specific domains should be minimized. Our validation toolkit TIC allows to explore the be- haviour of various algorithms for learning formal lan- guages. This is a well-examined and standardized ap- plication domain. TIC is operated by interactive as well as automatic control. |
Year | Venue | Keywords |
---|---|---|
2000 | FLAIRS Conference | formal language learning,automatic control,formal language |
Field | DocType | ISBN |
Common sense,Formal language,Computer science,Impression,Automatic control,Heuristics,Application domain,Natural language processing,Artificial intelligence,Instrumental and intrinsic value | Conference | 1-57735-113-4 |
Citations | PageRank | References |
2 | 0.39 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Volker Dötsch | 1 | 18 | 2.98 |
Klaus P. Jantke | 2 | 831 | 123.18 |