How to find Markov Blanket
Markov Blanket Definition
In a Bayesian network, the Markov Blanket of a node is the set of the nodes comprises of the node’s parents, its children and its co-parents.
Definition: Co-parents of a node are the parents of its children.
Let us consider a Bayesian network as shown in Figure 1.
Let us now find out the Markov Blanket of X4, the node highlighted in red in Figure 2.
Figure 3 shows the Markov Blanket of X4. X1 and X2 are the parents of X4, X7 and X9 are the children of X4 while X6 is the co-parent of X4.
Utility of Markov Blanket
In a Bayesian network, a node X is conditionally independent of all other nodes in the network given the Markov blanket. Additionally, the Markov blanket d-separates X from all other nodes in the network.
Subscribe to Our monthly newsletter for exciting data science news and learnings
Subscribe to our monthly newsletter, DataTrain, our thought train on all things data.