6.1 Bayesian Learning
6.1 Bayesian Learning
Instructor
Dr. Sanjay Chatterji
Importance
● Among the most practical approaches to certain
types of problems.
● Provides useful perspective for understanding
many learning algorithms.
− Find-S
− Candidate Elimination Algorithm
− Neural Network
● Bayesian perspective of Ockham’s Razor
Features of Bayesian learning methods
● Each observed training example can incrementally
decrease or increase the estimated probability that a
hypothesis is correct.
● Prior knowledge can be combined with observed data
to determine the final probability of a hypothesis.
● Bayesian methods can accommodate hypotheses that
make probabilistic predictions.
● New instances can be classified by combining the
predictions of multiple hypotheses.
Bayes Theorem
● In machine learning, we try to determine the best
hypothesis from some hypothesis space H, given the
observed training data D.
● The best hypothesis means the most probable
hypothesis, given the data D plus any initial knowledge
about the prior probabilities of the various hypotheses
in H.
● Calculate the probability of a hypothesis based on its
prior probability, the probabilities of observing various
data given the hypothesis, and the observed data
itself.
Notations
P(Norman late)=P(Norman
late|Trainstrike)*P(Train
strike) + P(Norman
late|¬train strike)*P(¬train
strike)=(0.8*0.1)*(0.1*0.9)=0.17
Bayesian Belief Network – Example
Thank You