Learning monotone term decision lists

We study the learnability of monotone term decision lists in the exact model of equivalence and membership queries. We show that, for any constant k>0, k-term monotone decision lists are exactly and properly learnable with n^O(k) membership queries in O(n^(k^3)) time. We also show n^Omega(k) memb...

ver descrição completa

Detalhes bibliográficos
Autores: Guijarro Guillem, David, Lavín Puente, Víctor Angel, Raghavan, Vijay
Tipo de documento: relatório científico
Data de publicação:1996
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:2117/83105
Acesso em linha:https://hdl.handle.net/2117/83105
Access Level:Acceso aberto
Palavra-chave:Learning monotone
Decision lists
Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica
Descrição
Resumo:We study the learnability of monotone term decision lists in the exact model of equivalence and membership queries. We show that, for any constant k>0, k-term monotone decision lists are exactly and properly learnable with n^O(k) membership queries in O(n^(k^3)) time. We also show n^Omega(k) membership queries are necessary for exact learning. In contrast, both k-term monotone decision lists (k>1) and general monotone decision lists are not learnable with equivalence queries alone.