decode.cutset {CRF} | R Documentation |
Decoding method for graphs with a small cutset
Description
Computing the most likely configuration for CRF
Usage
decode.cutset(
crf,
cutset,
engine = "default",
start = apply(crf$node.pot, 1, which.max)
)
Arguments
crf |
The CRF |
cutset |
A vector of nodes in the cutset |
engine |
The underlying engine for cutset decoding, possible values are "default", "none", "exact", "chain", and "tree". |
start |
An initial configuration, a good start will significantly reduce the seraching time |
Details
Exact decoding for graphs with a small cutset using cutset conditioning
Value
This function will return the most likely configuration, which is a vector of length crf$n.nodes
.
Examples
library(CRF)
data(Small)
d <- decode.cutset(Small$crf, c(2))
[Package CRF version 0.4-3 Index]