CODEWITHSUNDEEP
artificial-intelligenceprobabilitybayesian-networks
Einar Johnsen
Einar Johnsen

Reputation: 95

Bayesian Network creating conditional probability table (CPT)

I have trouble understanding where the numbers in the P(A|B,E) table are coming from in the alarm burglary example. I understand that P(B) and P(E) is chosen from knowledge about the domain. But I do not understand how many of the values in the CPT which can be chosen and which has to be calculated in order to make the tables valid. I assume that the P(J|A) and P(J|¬A) are chosen by expert knowledge? And then it must be the same for P(J|M).. or would these also have to be calculated by using given values?

I see with a binary example which is given here in the table on page 7: https://cseweb.ucsd.edu/~elkan/250A/bayesnets.pdf, they are using the same numbers, but how have they calculated the values 0.95, 0.94, 0.29 and 0.001?

burglary example

Upvotes: 3

Views: 7675

Answers (1)

ziggystar
ziggystar

Reputation: 28670

All the values in CPTs must come from somewhere, and cannot be calculated from other CPTs. There are two major approaches to get the numbers:

  1. Have a domain expert specify the numbers.
  2. Have a data set that contains joint realizations of the random variables. Then the numbers within the CPTs can be calculated from the respective frequencies within the data set. Note that this procedure becomes more complicated when not all variables are observed within the data set.

In addition, it is possible to mix approach 1 and 2.

Upvotes: 2

Related Questions