Learning deterministic linear languages (2002) [5 citations — 2 self]
Download:
|
|
by Colin De La Higuera
In: Computational Learning Theory, COLT 02. Number 2375 in Lecture Notes in Artificial Intelligence
ftp://altea.dlsi.ua.es/people/oncina/articulos/colt2002.ps
Add To MetaCart
Abstract:
Abstract. Linearity and determinism seem to be two essential conditions for polynomial language learning to be possible. We compare several definitions of deterministic linear grammars, and for a reasonable definition prove the existence of a canonical normal form. This enables us to obtain positive learning results in case of polynomial learning from a given set of both positive and negative examples. The resulting class is the largest one for which this type of results has been obtained so far. 1
Citations
| 274 | Cryptographic limitations on learning Boolean formulae and finite automata – Kearns, Valiant - 1994 |
| 72 | The minimum consistent DFA problem cannot be approximated within any polynomial – Pitt, Warmuth - 1993 |
| 46 | Recent advances of grammatical inference – Sakakibara - 1997 |
| 32 | Characteristic sets for polynomial grammatical inference – Higuera - 1997 |
| 21 | Identifying regular languages in polynomial time – Oncina, Garcia - 1992 |
| 13 | A hierarchy of language families learnable by regular language learners – Takada - 1994 |
| 12 | Learning of context-free languages: A survey of the literature – Lee - 1996 |
| 6 | A characterisation of Even Linear Languages and its application to the Learning Problem – Sempere, García - 1994 |
