evidence+theory 源代码

% Check that adding soft evidence to a hidden node is equivalent to evaluating its leaf CPD. % Make an HMM T = 3; Q = 2; O = 2; c…

% Compare Kalman smoother with loopy seed = 0; rand('state', seed); randn('state', seed); nlandmarks = 6; T = 12; [A,B,C,Q,R,Qbi…

function [err, time, engine] = cmp_inference(bnet, engine, exact, T, filter, singletons, maximize) % CMP_INFERENCE Compare several…

% to test whether scg inference engine can handl dynameic BN % Make a linear dynamical system % X1 -> X2 % | | % v …

% We consider a switching Kalman filter of the kind studied % by Zoubin Ghahramani, i.e., where the switch node determines % which…

%bnet = mk_motif_hhmm('motif_pattern', 'acca', 'background', 't'); bnet = mk_motif_hhmm('motif_pattern', 'accaggggga', 'backgroun…

% Make the following HHMM % % LH RH % / \ % / \ % LR -> UD …

% a multigram is a degenerate 2HHMM where the bottom level HMMs emit deterministic strings % and the the top level abstract states…

% like mgram1, except we use a durational HMM instead of an HHMM2 past = 0; words = {'the', 't', 'h', 'e'}; data = 'the'; nwords…

% like mgram2, except we unroll the DBN so we can use smaller % state spaces for the early duration nodes: % the state spaces are …