Learnability of Kolmogorov-easy circuit expressions via queries

Circuit expressions were introduced to provide a natural link between Computational Learning and certain aspects of Structural Complexity. Upper and lower bounds on the learnability of circuit expressions are known. We study here the case in which the circuit expressions are of low (time-bounded) Ko...

ver descrição completa

Detalhes bibliográficos
Autores: Balcázar Navarro, José Luis|||0000-0003-4248-4528, Buhrman, H, Hermo, M
Tipo de documento: relatório científico
Data de publicação:1995
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:2117/96996
Acesso em linha:https://hdl.handle.net/2117/96996
Access Level:Acceso aberto
Palavra-chave:Circuit expressions
Learnability
Structural complexity
Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica
Descrição
Resumo:Circuit expressions were introduced to provide a natural link between Computational Learning and certain aspects of Structural Complexity. Upper and lower bounds on the learnability of circuit expressions are known. We study here the case in which the circuit expressions are of low (time-bounded) Kolmogorov complexity. We show that these are polynomial-time learnable from membership queries in the presence of an NP oracle. We also exactly characterize, in terms of advice classes, the sets that have such easy circuit expressions, obtain consequences regarding their lowness, and precisely identify the subclass whose circuit expressions can be learned from membership queries alone, by means of doubly tally polynomial time degrees. The extension of the results to various Kolmogorov complexity bounds is discussed.