VE dimension induced by Bayesian networks over the boolean domain
Y Yang, Y Wu - Pattern Analysis and Applications, 2014 - Springer
Y Yang, Y Wu
Pattern Analysis and Applications, 2014•SpringerIn this paper, we focus on the concept classes C _ N induced by Bayesian networks. The
relationship between two-dimensional values induced by these concept classes is studied,
one of which is the VC-dimension of the concept class C _ N, denoted as VCdim (N), and
other is the smallest dimensional of Euclidean spaces into which C _ N can be embedded,
denoted as Edim (N). As a main result, we show that the two-dimensional values are equal
for the Bayesian networks with n≤ 4 variables, called the VE-dimension for that Bayesian …
relationship between two-dimensional values induced by these concept classes is studied,
one of which is the VC-dimension of the concept class C _ N, denoted as VCdim (N), and
other is the smallest dimensional of Euclidean spaces into which C _ N can be embedded,
denoted as Edim (N). As a main result, we show that the two-dimensional values are equal
for the Bayesian networks with n≤ 4 variables, called the VE-dimension for that Bayesian …
Abstract
In this paper, we focus on the concept classes induced by Bayesian networks. The relationship between two-dimensional values induced by these concept classes is studied, one of which is the VC-dimension of the concept class denoted as and other is the smallest dimensional of Euclidean spaces into which can be embedded, denoted as As a main result, we show that the two-dimensional values are equal for the Bayesian networks with n ≤ 4 variables, called the VE-dimension for that Bayesian networks.
Springer
Showing the best result for this search. See all results