com.cra.figaro.algorithm.factored.beliefpropagation
OneTimeProbEvidenceBeliefPropagation
The algorithm to compute probability of specified evidence in a dependent universe.
The algorithm to compute probability of specified evidence in a dependent universe. We use () => Double to represent this algorithm instead of an instance of ProbEvidenceAlgorithm. Typical usage is to return the result of ProbEvidenceAlgorithm.computeProbEvidence when invoked.
A list of universes that depend on this universe such that evidence on those universes should be taken into account in this universe.
A list of universes that depend on this universe such that evidence on those universes should be taken into account in this universe.
Since BP uses division to compute messages, the semiring has to have a division function defined
Since BP uses division to compute messages, the semiring has to have a division function defined
Target elements that should not be eliminated but should be available for querying.
Target elements that should not be eliminated but should be available for querying.
The algorithm used to compute the probability of additional evidence, as created by probAdditionalEvidence.
The algorithm used to compute the probability of additional evidence, as created by probAdditionalEvidence. This algorithm can be different to the one defined in this class. (For example, a one-time algorithm can use an anytime algorithm for additional evidence.)
Returns the product of all messages from a source node's neighbors to itself.
Returns the product of all messages from a source node's neighbors to itself.
Removes the evidence provided in the constructor from the universe.
Removes the evidence provided in the constructor from the universe.
Compute the evidence of the model.
Compute the evidence of the model. Returns the probability of evidence on the model. This assumes that BP has already been run on this algorithm instance.
By default, implementations that inherit this trait have no debug information.
By default, implementations that inherit this trait have no debug information. Override this if you want a debugging option.
Get the belief for an element.
Get the belief for an element.
Returns the factors needed for BP.
Returns the factors needed for BP. Since BP operates on a complete factor graph, factors are created for all elements in the universe.
Get the final factor for an element.
Get the final factor for an element.
Get the elements that are needed by the query target variables and the evidence variables.
Get the elements that are needed by the query target variables and the evidence variables. Also compute the values of those variables to the given depth. Only get factors for elements that are actually used by the target variables. This is more efficient. Also, it avoids problems when values of unused elements have not been computed.
In addition to getting all the needed elements, it determines if any of the conditioned, constrained, or dependent universe parent elements has * in its range. If any of these elements has * in its range, the lower and upper bounds of factors will be different, so we need to compute both. If they don't, we don't need to compute bounds.
Since probability of evidence algorithms introduce additional evidence (namely, their evidence argument), into an existing universe, a mechanism must be provided for introducing the evidence when the algorithm begins and cleaning it up at the end.
Since probability of evidence algorithms introduce additional evidence (namely, their evidence argument), into an existing universe, a mechanism must be provided for introducing the evidence when the algorithm begins and cleaning it up at the end. This is achieved with the initialize method, called when the algorithm starts, and the cleanUp method, called when the algorithm is killed.
Kill the algorithm so that it is inactive.
Kill the algorithm so that it is inactive. It will no longer be able to provide answers.Throws AlgorithmInactiveException if the algorithm is not active.
The computed log probability of evidence.
The computed log probability of evidence.
Normalize a factor.
Normalize a factor.
Returns an algorithm to compute the probability of the additional evidence provided.
Returns an algorithm to compute the probability of the additional evidence provided.
The computed probability of evidence.
The computed probability of evidence.
Returns the probability of evidence of the universe on which the algorithm operates.
Returns the probability of evidence of the universe on which the algorithm operates. Throws AlgorithmInactiveException if the algorithm is not active.
Resume the computation of the algorithm, if it has been stopped.
Resume the computation of the algorithm, if it has been stopped. Throws AlgorithmInactiveException if the algorithm is not active.
Run the algorithm, performing its computation to completion.
Run the algorithm, performing its computation to completion.
Runs this belief propagation algorithm for one iteration.
Runs this belief propagation algorithm for one iteration. An iteration consists of each node of the factor graph sending a message to each of its neighbors.
Start the algorithm and make it active.
Start the algorithm and make it active. After it returns, the algorithm must be ready to provide answers. Throws AlgorithmActiveException if the algorithm is already active.
Elements towards which queries are directed.
Elements towards which queries are directed. By default, these are the target elements. This is overridden by DecisionVariableElimination, where it also includes utility variables.
Stop the algorithm from computing.
Stop the algorithm from computing. The algorithm is still ready to provide answers after it returns. Throws AlgorithmInactiveException if the algorithm is not active.
Trait for One Time BP evidence algorithms.