enter_evidence.m

来自「Bayes网络工具箱」· M 代码 · 共 13 行

function [engine, loglik] = enter_evidence(engine, evidence, filter)
% ENTER_EVIDENCE Add the specified evidence to the network (jtree_unrolled_dbn)
% [engine, loglik] = enter_evidence(engine, evidence, filter)
%
% evidence{i,t} = [] if if X(i,t) is hidden, and otherwise contains its observed value (scalar or column vector)
% filter, if specified, must be 0: this algorithm always does smoothing.

if nargin < 3, filter = 0; end
assert(filter == 0);
assert(size(evidence,2) == engine.nslices);
[engine.sub_engine, loglik] = enter_evidence(engine.sub_engine, evidence);