Abstract | ||
---|---|---|
This paper examines the learnability of a major subclass of E-pattern languages - also known as erasing or extended pattern languages - in Cold's learning model: We show that the class of terminal-free E-pattern languages is inferrable from positive data if the corresponding terminal alphabet consists of three or more letters. Consequently, the recently presented negative result for binary alphabets is unique. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-24749-4_12 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
pattern language | Discrete mathematics,Subclass,Inference,Computer science,Discontinuity (linguistics),Theoretical computer science,Artificial intelligence,Learnability,Binary number,Alphabet | Conference |
Volume | ISSN | Citations |
2996 | 0302-9743 | 9 |
PageRank | References | Authors |
0.64 | 17 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Reidenbach | 1 | 154 | 18.06 |