The Consistency dimension and distribution-dependent learning from queries

We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then w...

ver descrição completa

Detalhes bibliográficos
Autores: Balcázar Navarro, José Luis|||0000-0003-4248-4528, Castro Rabal, Jorge|||0000-0002-1390-1313, Guijarro Guillem, David
Tipo de documento: relatório científico
Data de publicação:2000
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/95948
Acesso em linha:https://hdl.handle.net/2117/95948
Access Level:Acceso aberto
Palavra-chave:Combinatorial characterization
Polynomial learnability
Query learning
Àrees temàtiques de la UPC::Informàtica
Descrição
Resumo:We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on the instance space, both as an application of the tools developed from the combinatorial characterization and as models of independent interest.