Exact learning of subclasses of CDNF formulas with membership queries
We consider the exact learnability of subclasses of Boolean formulas from membership queries alone. We show how to combine known learning algorithms that use membership and equivalence queries to obtain new learning results only with memberships. In particular we show the exact learnability of read-...
| Autor: | |
|---|---|
| Formato: | informe técnico |
| Fecha de publicación: | 1996 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | español |
| OAI Identifier: | oai:upcommons.upc.edu:2117/96475 |
| Acesso em linha: | https://hdl.handle.net/2117/96475 |
| Access Level: | acceso abierto |
| Palavra-chave: | Learnability Boolean formulas Learning algorithms CDNF Àrees temàtiques de la UPC::Informàtica |
| Resumo: | We consider the exact learnability of subclasses of Boolean formulas from membership queries alone. We show how to combine known learning algorithms that use membership and equivalence queries to obtain new learning results only with memberships. In particular we show the exact learnability of read-k monotone formulas, Sat-k O(log n)-CDNF, and O(sqrt{log n})-size CDNF from membership queries only. |
|---|