Structure learning of Bayesian networks via data perturbation

Structure learning of Bayesian networks via data perturbation

Structure learning of Bayesian Networks (BNs) is an NP-hard problem, and the use of sub-optimal strategies is essential in domains involving many variables. One of them is to generate multiple approximate structures and then to reduce the ensemble to a representative structure. It is possible to...

Full description

Bibliographic Details
Main Author: Tadeu Junior Gross
Other Authors: Carlos Dias Maciel
Language:English
Published: Universidade de São Paulo 2018
Subjects:
Aprendizado de estruturas robustas
D-separação
Descoberta de associações
Envelhecimento da população
Estabilidade de arcos
Expressão fechada para calcular a frequência-de-corte
Fatores de risco
Grafo acíclico dirigido
limiar analítico
Média de modelos
Perturbação de dados via bootstrap
Rede Bayesiana
Síndrome metabólica
Transtorno cognitivo
Analytical threshold
Associations discovery
Bayesian network
Closed-form expression to compute the cutoff-frequency
Cognitive impairment
D-separation
Data perturbation via bootstrap replicas
Directed acyclic graph
Learning of robust structures
Metabolic syndrome
Model averaging
Population ageing
Risk factors
Stability of arcs
Online Access:http://www.teses.usp.br/teses/disponiveis/18/18153/tde-19022019-134517/

Similar Items

Similar Items