Daniel@0: % Compare various inference engines on the following network (from Jensen (1996) p84 fig 4.17)
Daniel@0: %    1
Daniel@0: %  / | \
Daniel@0: % 2  3  4
Daniel@0: % |  |  |
Daniel@0: % 5  6  7
Daniel@0: %  \/ \/
Daniel@0: %  8   9
Daniel@0: % where all arcs point downwards
Daniel@0: 
Daniel@0: N = 9;
Daniel@0: dag = zeros(N,N);
Daniel@0: dag(1,2)=1; dag(1,3)=1; dag(1,4)=1;
Daniel@0: dag(2,5)=1; dag(3,6)=1; dag(4,7)=1;
Daniel@0: dag(5,8)=1; dag(6,8)=1; dag(6,9)=1; dag(7,9) = 1;
Daniel@0: 
Daniel@0: dnodes = 1:N;
Daniel@0: false = 1; true = 2;
Daniel@0: ns = 2*ones(1,N); % binary nodes
Daniel@0: 
Daniel@0: onodes = [1];
Daniel@0: evidence = cell(1,N);
Daniel@0: evidence(onodes) = num2cell(1);
Daniel@0: bnet = mk_bnet(dag, ns, 'observed', onodes);
Daniel@0: % use random params
Daniel@0: %for i=1:N
Daniel@0: %  bnet.CPD{i} = tabular_CPD(bnet, i);
Daniel@0: %end
Daniel@0: bnet.CPD{1} = tabular_CPD(bnet, 1, 'sparse', 1, 'CPT', [0.8, 0.2]);
Daniel@0: bnet.CPD{2} = tabular_CPD(bnet, 2, 'sparse', 1, 'CPT', [1 0 0 1]);
Daniel@0: bnet.CPD{3} = tabular_CPD(bnet, 3, 'sparse', 1, 'CPT', [0 1 1 0]);
Daniel@0: bnet.CPD{4} = tabular_CPD(bnet, 4, 'sparse', 1, 'CPT', [1 1 0 0]);
Daniel@0: bnet.CPD{5} = tabular_CPD(bnet, 5, 'sparse', 1, 'CPT', [0 0 1 1]);
Daniel@0: bnet.CPD{6} = tabular_CPD(bnet, 6, 'sparse', 1, 'CPT', [1 0 0 1]);
Daniel@0: bnet.CPD{7} = tabular_CPD(bnet, 7, 'sparse', 1, 'CPT', [0 1 1 0]);
Daniel@0: bnet.CPD{8} = tabular_CPD(bnet, 8, 'sparse', 1, 'CPT', [1 1 0 0 0 0 1 1]);
Daniel@0: bnet.CPD{9} = tabular_CPD(bnet, 9, 'sparse', 1, 'CPT', [0 1 0 1 1 0 1 0]);
Daniel@0: 
Daniel@0: engine = jtree_sparse_inf_engine(bnet);
Daniel@0: tic
Daniel@0: [engine, ll] = enter_evidence(engine, evidence);
Daniel@0: toc
Daniel@0: