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-...

Descripción completa

Detalles Bibliográficos
Autor: Domingo, Carlos
Tipo de recurso: informe técnico
Fecha de publicación:1996
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:español
OAI Identifier:oai:upcommons.upc.edu:2117/96475
Acceso en línea:https://hdl.handle.net/2117/96475
Access Level:acceso abierto
Palabra clave:Learnability
Boolean formulas
Learning algorithms
CDNF
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario: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.