wolffd@0: % Make an HMM with autoregressive Gaussian observations (switching AR model)
wolffd@0: %   X1 -> X2
wolffd@0: %   |     | 
wolffd@0: %   v     v
wolffd@0: %   Y1 -> Y2 
wolffd@0: 
wolffd@0: seed = 0;
wolffd@0: rand('state', seed);
wolffd@0: randn('state', seed);
wolffd@0: 
wolffd@0: intra = zeros(2);
wolffd@0: intra(1,2) = 1;
wolffd@0: inter = zeros(2);
wolffd@0: inter(1,1) = 1;
wolffd@0: inter(2,2) = 1;
wolffd@0: n = 2;
wolffd@0: 
wolffd@0: Q = 2; % num hidden states
wolffd@0: O = 2; % size of observed vector
wolffd@0: 
wolffd@0: ns = [Q O];
wolffd@0: dnodes = 1;
wolffd@0: onodes = [2];
wolffd@0: bnet = mk_dbn(intra, inter, ns, 'discrete', dnodes, 'observed', onodes);
wolffd@0: 
wolffd@0: bnet.CPD{1} = tabular_CPD(bnet, 1);
wolffd@0: bnet.CPD{2} = gaussian_CPD(bnet, 2);
wolffd@0: bnet.CPD{3} = tabular_CPD(bnet, 3);
wolffd@0: bnet.CPD{4} = gaussian_CPD(bnet, 4);
wolffd@0: 
wolffd@0: 
wolffd@0: T = 10; % fixed length sequences
wolffd@0: 
wolffd@0: engine = {};
wolffd@0: %engine{end+1} = hmm_inf_engine(bnet);
wolffd@0: engine{end+1} = jtree_unrolled_dbn_inf_engine(bnet, T);
wolffd@0: %engine{end+1} = smoother_engine(hmm_2TBN_inf_engine(bnet));
wolffd@0: %engine{end+1} = smoother_engine(jtree_2TBN_inf_engine(bnet));
wolffd@0: 
wolffd@0: inf_time = cmp_inference_dbn(bnet, engine, T, 'check_ll',1);
wolffd@0: learning_time = cmp_learning_dbn(bnet, engine, T, 'check_ll', 1);
wolffd@0: