infer.conditional function

Conditional inference method

Computing the partition function and marginal probabilities

infer.conditional(crf, clamped, infer.method, ...)

Arguments

• crf: The CRF
• clamped: The vector of fixed values for clamped nodes, 0 for unfixed nodes
• infer.method: The inference method to solve the clamped CRF
• ...: The parameters for infer.method

Returns

This function will return a list with components: - node.bel: Node belief. It is a matrix with crf$n.nodes rows and crf$max.state columns.

• edge.bel: Edge belief. It is a list of matrices. The size of list is crf$n.edges and the matrix i has crf$n.states[crf$edges[i,1]] rows and crf$n.states[crf$edges[i,2]] columns.

• logZ: The logarithmic value of CRF normalization factor Z.

Details

Conditional inference (takes another inference method as input)

Examples

library(CRF)
data(Small)
i <- infer.conditional(Small$crf, c(0,1,0,0), infer.exact)