wolffd@0: function post = compute_posterior_dbn(bnet, state, i, n, strides, families, ...
wolffd@0: 				  CPT)
wolffd@0: % COMPUTE_POSTERIOR
wolffd@0: %
wolffd@0: % post = compute_posterior(bnet, state, i, n, strides, families,
wolffd@0: % cpts)
wolffd@0: %
wolffd@0: % Compute the posterior distribution on node X_i^n of a DBN,
wolffd@0: % conditional on evidence in the cell array state
wolffd@0: %
wolffd@0: % strides is the cached result of compute_strides(bnet)
wolffd@0: % families is the cached result of compute_families(bnet)
wolffd@0: % cpt is the cached result of get_cpts(bnet)
wolffd@0: %
wolffd@0: % post is a one-dimensional table
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: % First multiply in the cpt of the node itself
wolffd@0: post = get_slice_dbn(bnet, state, i, n, i, n, strides, families, CPT);
wolffd@0: post = post(:);
wolffd@0: 
wolffd@0: % Then multiply in CPTs of children that are in this slice
wolffd@0: for j = children(bnet.intra, i)
wolffd@0:   slice = get_slice_dbn(bnet, state, j, n, i, n, strides, families, CPT);
wolffd@0:   post = post.*slice(:);
wolffd@0: end
wolffd@0: 
wolffd@0: % Finally, if necessary, multiply in CPTs of children in the next
wolffd@0: % slice 
wolffd@0: if (n < size(state,2))
wolffd@0:   for j = children(bnet.inter, i)
wolffd@0:     slice = get_slice_dbn(bnet, state, j, n+1, i, n, strides, families, ...
wolffd@0: 			    CPT);
wolffd@0:     post = post.*slice(:);
wolffd@0:   end
wolffd@0: end
wolffd@0: 
wolffd@0: post = normalise(post);
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: 
wolffd@0: