[关闭]
@nanmeng 2016-05-05T08:02:20.000000Z 字数 1433 阅读 1205

Probabilistic Graphical Models(Stanford) - 2

notes Probabilistic_Graphical_Models


Week1 Template Models

1. Overview of Template Models

There are some ''patterns'' are sharing between models within this model.
PGM1_30
PGM1_31

  • sharing across pixel
  • sharing pair of supperpixels
  • sharing between and within a model

examples:
PGM1_32
PGM1_33

Template Variables:
PGM1_34

Template Models:
PGM1_35

Which of the following are advantages of using template models?

2. Template Models - DBNs

PGM1_36

Markov Assumption

PGM1_37
The equation above do not make any assumption!!! we only re-expressing the
probability distribution in the way that time flows forward

Add the independent assumption
PGM1_38
which means that the next step is independent of the past given the present.
PGM1_39
the equation above is acquired based on the independent assumption
An example of showing that the Markov assumption sometimes is too strong.
PGM1_40

Time Invariance

PGM1_41
Time invariance states that the states of system change from one to another is independent of the current time.
we can enrich the model by including some other conditions.
PGM1_43
PGM1_44
PGM1_45

Dynamic Bayesian Network

PGM1_46
PGM1_47

Summary

PGM1_48

3. Temporal Models - HMMs

PGM1_49

Numerous Application

  • Robot Localization
    PGM1_50
  • Speech Recognition
    PGM1_51
    PGM1_52
    Phones matters much(Phonetic Alphabet).
  • Word HMM
    PGM1_53
    PGM1_54
    PGM1_55 this is the whole system.

Summary

PGM1_56

4. Plate Models

is the actual CPD parameter
is outside the plate which means it is not indexed by which also means it is the same for all values of .
PGM1_57
PGM1_58

Nested Plates

The variable in the nested plates are indexed by both.
PGM1_59

Overlapping Plates

PGM1_60
PGM1_61

Plate Dependency Model

PGM1_62
PGM1_63

Summary

PGM1_64

添加新批注
在作者公开此批注前,只有你和作者可见。
回复批注