### Assignment on Probabilistic Graphical Model

Added on - 09 Oct 2019

5

pages

1315

words

97

views

0

downloads

Showing pages 1 to 2 of 5 pages

Bayesian Network helps utilize the probabilities in the Artificial Intelligence. It is a form ofprobabilistic graphical model. The model shows the dependencies among the variables. Oneof the examples of the model can be the representation of diseases and the symptoms. If thesymptoms are available with the individual then the individual can use the tool to understandthe likeliness of various diseases. The representation of the network is through arrows andnodes. The nodes present in the model denote the quantities that can be identified by theobservers. In some cases, there are variables that are not known completely but can beinferred from the situation. Such variables are called latent variables, which are also used asthe nodes (Jensen, 1996). Moreover, there are hypothetical variables defined by theindividuals to understand the situations that are also denoted on the nodes of the models. Thediagram given below shows the simple model of the network consisting of nodes and thedependencies shown through arrows:The variables shown through the nodes are represented as X = X1+X2+...Xnand the arcs thatare shown in the diagram above is represented by Xi→Xj. The arcs shows the directdependencies among the variables they are connected. One of the important aspects that areused in this network is the conditional probability. The conditional probability shows thestrengths of the dependencies. However, one thing that should be kept in consideration whileforming the nodes and arcs is that the directed cycles should not there (Nielsen 7 Jensen,

2009 ). If an individual wants to return to a node by moving through the directed arcs, then itwould not reach feasible solution.As per the inference is concerned, there are three of these within BN. They are given below:Inferring unobserved variablesDue to the presence of all the observed variables in the Bayesian Network, it becomes easierto infer the variables that are unobserved. Answering the queries with the help of probabilitybecomes easier (Murphy, 2002).Parameter learningParameters are used to show the likelihood of one cause over another. The parameters aregenerally unknown and require estimation.Structure learningThe structures are defined in BNs with the help of experts and then inferences are derived.Data are used to form the structure as in most cases it becomes challenging due to itscomplexity.The construction of Bayesian Networ requires understanding few steps. These steps are givenbelow:Nodes and valuesThis is the first step where the individual tries to understand the variables that are into play.There are some questions that are considered while selecting the variables for the nodes suchas the values that are applicable, or the state in which they are, and others. The discrete nodeshave been preferred here for discussion (Heckerman, 1998). Some of general discrete nodestypes are Boolean nodes, ordered nodes, and integral nodes. The Boolean nodes refer to the

**You’re reading a preview**

To View Complete Document

Become a Desklib Library Member.

Subscribe to our plans