Saturday, October 22, 2011

Bayes Network and Bayes Rule

As explained by Sebastin Thrun in the AI course:

Bayes Rule:



Whats the likelihood that a person has cancer (A) given that they have had a positive cancer diagnostic test (B)?

  • Likelihood: Probability of +ve cancer test (B) given that the person has cancer (A)
  • Prior: Probability of getting that type of cancer (A)
  • Marginal likelihood: Sum of probability of
    (+ve test given that you have the cancer x probability of having that cancer)
    (+ve test given that you don’t have the cancer (false positive) x probability of not having that cancer)

Bayes Network:



Inferring P(B):


Baye’s Rule:

Baye’s Network:

No comments: