人工智能入门（四）：uncertainty&基于统计的学习

1.belief networks (indenpendence, collider，conditioning / marginalization，connection graph，independence in belief networks，D-separation，uncertain and unreliable evidence）Belief and Markov Networks

2.inference, general inference(variable elimination，bucket elimination algorithm), message passing idea(sum-product algorithm,`belief propagation' or `dynamic programming',max-product algorithm,loop-cut conditioning) 

for singly connected graphs: sum-product, max-product;

for multiply connected graphs: loop-cut conditioning, bucket elimination;

3.MAP,ML,(KL Divergence),Naive Bayes Classier,Using a Beta prior

4.dealing with miss variables: Missing Completely at random (MCAR), Missing at random(MAR),Missing NOT at random (MNAR),Expectation Maximisation(EM algorithm)

5.sampling（univariate，rejection，multi-variate,ancestral, Gibbs, importance, sequential importance,particle filter）

6.dynamical models(HMM(filtering, smoothing,prediction),Viterbi, Kalman, particle Filtering (bootstrap filtering)