dynamic bayesian networks (dbns)
DESCRIPTION
Dynamic Bayesian Networks (DBNs). Dave, Hsieh Ding Fei Frank, Yip Keung. Outline. Introduction to DBNs Inference in DBNs Type of inference Exact inference Approximate inference Applications Conclusion. Introduction to DBNs. Motivation Bayesian Network (BN) Models - PowerPoint PPT PresentationTRANSCRIPT
Dynamic Bayesian Networks (DBNs)
Dave, Hsieh Ding Fei
Frank, Yip Keung
Outline Introduction to DBNs Inference in DBNs
Type of inference Exact inference Approximate inference
Applications Conclusion
Introduction to DBNs Motivation
Bayesian Network (BN) Models Static nature of the problem domain Observable quantity is observed once for all Confidence in the observation is true for all time
DBN Domains involving repeated observations Process dynamically evolves over time Examples: Monitoring a patient, traffic monitoring,
etc.
Introduction to DBNs Assumptions
The process is modeled as discrete time-slice At time 1, state is X(1) , at time t, state is X(t) P(X(1),…, X(t))=P(X(1)) P(X(1)|X(2) )…P(X(t)|X(1),…, X(t-1))
Markov property Given current state, the next state is independent of
previous states P(X(1),…, X(t))=P(X(1)) P(X(1)|X(2) )…P(X(t)|X(t-1))
Introduction to DBNs DBN model (DAG representation)
Edge means how tight the coupling is between nodes
Effect is immediateedge within same time slice Effect is long termedge between time slices
Introduction to DBNs Special case of DBN HMM
State of HMM evolves in a Markovian way Model HMM as a simple DBN
Each time slice contains two variables which are state q and observation o
Inference Type of Inference
Prediction Given a probability distribution over current state,
predict the distribution over future states
Monitoring Given the observation (evidence) in every time slice t,
maintain the distribution over the current state Belief state at time T P(X(T) | o(1) ,…, o(T))
Inference Probability Estimation
Given a sequence of observations in every time slice t,determine the distribution over each intermediate state
P(X(t) | o(1) ,…, o(T)) for t = 1, 2, … , T
Explanation Given an initial state and a sequence of observations
o(1) ,…, o(T), determine the most likely sequence of states X(1) ,…, X(T)
Exact inference For most inference tasks, a belief state need to be
maintained belief state
A probability distribution over the current state This state summarize all information about
history Need to be maintained compactly
Exact inference How to accomplish exact inference How to do this in a simple DBN HMM
Given a number of time slices, the DBN is just a very long BN with regular structure
Standard Bayesian network algorithms can be used
Probability estimation task Clique tree propagation algorithm Forward-backward algorithm
Exact inference Monitoring task
Only the forward pass of forward-backward algorithm
Explanation task Viterbi’s algorithm
Prediction task Only base on the current belief state because it
already have the history information
Exact inference dHugin : an exact inference computational
system Inference method of classical discrete time-series
analysis Allows discrete multivariate dynamic system
dHugin introduce notion of dynamic time window
Contain several time slice and represent by junction tree Operations: window expansion and reduction Expand window to perform forecasting Inference are formulated in terms of message passing in
junction tree
dHugin Window expansion
1. Move k new consecutive time slices to the forecast model
2. Move the k oldest time slices of the forecast model to the time window
3. Moralize the compound graph including the graph in window and the new k slices
4. Triangulate the time window
5. Construct new junction tree
dHugin Window reduction Suppose has k+1 time slices in time window
1. make the k oldest slices in time window become k backward smoothing models
2. The remain (k+1)’st slices is the new time window
Forecasting Calculate estimates of the distributions of future
variables given past observations and present variables
Forecasting within window Propagation
Forecasting beyond the window1. A series of alternating expansion and reduction
step
2. Propagation performed in each step
Problem of Exact inference Drawback: complex and require large space for computations Key issue is how to maintain the belief state
Represent it naively Require an exponential number of entries
Cannot represent it compactly by exploiting the structure no conditional independence structure Variables becomes correlated each other when time goes on Prevent using factorization ideas
Not even conditionally independent within this time slice
Approximate Inference
Objective Try to maintain and propagate an approximate
belief state when the state space is very large in dynamic process
It improves the complexity of probabilistic inference
Approximate Inference
Two approaches Structural approximation
Ignore weak correlations between variables in a belief state
Stochastic simulation Randomly sample from the states in the belief state
Structural Approximation Problems in exact inference
All variables in a belief state are correlated Belief state is expressed as full joint distribution
Need exponential number of table entries Objective of structural approximation
Use factorization in order to represent complex system compactly by exploiting the fact that each variable has weak interaction with each other
Structural Approximation Example (monitor a freeway with multiple cars)
States of different cars (e.g velocity,location..etc) become correlated after a certain period of time
Approximation is to assume that the correlations are not very strong
Each car can be considered as independent The approximate belief state can be represented
in a factorized way, as a product of separate distributions, one for each car
Structural Approximation We can define a set of disjoint clusters Y1,…, Yk
such that Y = Y1 Y2 … Yk . We maintain an approximate belief state :
If this approximate belief state of time t is simply propagated forward to time t+1, all variables would become correlated again
i
it YtYt )(ˆ)(ˆ )(
Structural Approximation It can be solved by executing the below process
At each time t, we take and propagate it to time t+1, obtain a new distribution
Approximate using independent marginal Compute for every I Ie.
The product of each marginal is
t̂1
~t
1~
t
)(1~ )1( t
iYt
)1()1( /
)1()1( )(1~
)(1~
ti
t YY
tti YtYt
1ˆ t
Structural Approximation Two sources of error
The accumulated error results from propagation The error results from approximation of
Errors are bounded due to two opposing forces Propagation from time t to time t+1 adds noise to
exact and approximate belief state reduce difference between them reduce error
Approximation increase error
1~
t
Stochastic Simulation
Likelihood Weighting (LW) Find the approximate belief state using sampling
Algorithm of LW
Stochastic Simulation
Drawback LW generates the samples at time t according to
prior distribution (depends on condition of samples at time t-1)
Observation affects the weights, but not the choice of samples
Samples generated get increasingly irrelevant when time grows as some samples are not likely to happen to explain the current observation
Example of monitoring car’s location
Stochastic Simulation
Samples at t = 5 are more distributed, far away from exact location of vehicle
An improved algorithm called Survival-Of-Fittest is used
Stochastic Simulation Survival-Of-Fittest (SOF)
Propagate likely samples more often than unlikely samples
Algorithm of SOF
Stochastic Simulation
Belief state propagation over time
(a) exact belief state
(b) belief state by using LW
(b) belief state by using SOF
Application Robot localization
Track a robot moving around in an environment State variables
x, y location Orientation
Transition model corresponds to motion Next position is a Gaussian around a linear function of
current position Observation model
Probability that sonar detect an obstacle
Conclusion Concept DBNs Inference in DBNs
Four types of inference Exact inference
dHugin Approximate inference
Structural approximation Search –based Stochastic simulation
Applications robot localization