wolffd@0: function CPD = hhmmQ_CPD(bnet, self, Qnodes, d, D, varargin)
wolffd@0: % HHMMQ_CPD Make the CPD for a Q node at depth D of a D-level hierarchical HMM
wolffd@0: % CPD = hhmmQ_CPD(bnet, self, Qnodes, d, D, ...)
wolffd@0: %
wolffd@0: %  Fd(t-1) \   Q1:d-1(t)
wolffd@0: %           \  |
wolffd@0: %            \ v
wolffd@0: %  Qd(t-1) -> Qd(t)
wolffd@0: %            /
wolffd@0: %           /
wolffd@0: %  Fd+1(t-1) 
wolffd@0: %
wolffd@0: % We assume parents are ordered (numbered) as follows:
wolffd@0: % Qd(t-1), Fd+1(t-1), Fd(t-1), Q1(t), ..., Qd(t)
wolffd@0: %
wolffd@0: % The parents of Qd(t) can either be just Qd-1(t) or the whole stack Q1:d-1(t) (allQ)
wolffd@0: % In either case, we will call them Qps.
wolffd@0: % If d=1, Qps does not exist. Also, the F1(t-1) -> Q1(t) arc is optional.
wolffd@0: % If the arc is missing, startprob does not need to be specified,
wolffd@0: % since the toplevel is assumed to never reset (F1 does not exist).
wolffd@0: % If d=D, Fd+1(t-1) does not exist (there is no signal from below).
wolffd@0: %
wolffd@0: % optional args [defaults]
wolffd@0: %
wolffd@0: % transprob - transprob(i,k,j) = prob transition from i to j given Qps = k ['leftright']
wolffd@0: % selfprob  - prob of a transition from i to i given Qps=k [0.1]
wolffd@0: % startprob - startprob(k,j) = prob start in j given Qps = k ['leftstart']
wolffd@0: % startargs - other args to be passed to the sub tabular_CPD for learning startprob
wolffd@0: % transargs - other args will be passed to the sub tabular_CPD for learning transprob
wolffd@0: % allQ      - 1 means use all Q nodes above d as parents, 0 means just level d-1 [0]
wolffd@0: % F1toQ1    - 1 means add F1(t-1) -> Q1(t) arc, 0 means level 1 never resets [0]
wolffd@0: %
wolffd@0: % For d=1, startprob(1,j) is only needed if F1toQ1=1
wolffd@0: % Also, transprob(i,j) can be used instead of transprob(i,1,j).
wolffd@0: %
wolffd@0: % hhmmQ_CPD is a subclass of tabular_CPD so we inherit inference methods like CPD_to_pot, etc.
wolffd@0: %
wolffd@0: % We create isolated tabular_CPDs with no F parents to learn transprob/startprob
wolffd@0: % so we can avail of e.g., entropic or Dirichlet priors.
wolffd@0: % In the future, we will be able to represent the transprob using a tree_CPD.
wolffd@0: %
wolffd@0: % For details, see "Linear-time inference in hierarchical HMMs", Murphy and Paskin, NIPS'01.
wolffd@0: 
wolffd@0: 
wolffd@0: ss = bnet.nnodes_per_slice;
wolffd@0: %assert(self == Qnodes(d)+ss);
wolffd@0: ns = bnet.node_sizes(:);
wolffd@0: CPD.Qsizes = ns(Qnodes);
wolffd@0: CPD.d = d;
wolffd@0: CPD.D = D;
wolffd@0: allQ = 0;
wolffd@0: 
wolffd@0: % find out which parents to use, to get right size
wolffd@0: for i=1:2:length(varargin)
wolffd@0:   switch varargin{i},
wolffd@0:    case 'allQ', allQ = varargin{i+1}; 
wolffd@0:   end
wolffd@0: end
wolffd@0: 
wolffd@0: if d==1
wolffd@0:   CPD.Qps = [];
wolffd@0: else
wolffd@0:   if allQ
wolffd@0:     CPD.Qps = Qnodes(1:d-1);
wolffd@0:   else
wolffd@0:     CPD.Qps = Qnodes(d-1);
wolffd@0:   end
wolffd@0: end
wolffd@0: 
wolffd@0: Qsz = ns(self);
wolffd@0: Qpsz = prod(ns(CPD.Qps));
wolffd@0: 
wolffd@0: % set default arguments
wolffd@0: startprob = 'leftstart';
wolffd@0: transprob = 'leftright';
wolffd@0: startargs = {};
wolffd@0: transargs = {};
wolffd@0: CPD.F1toQ1 = 0;
wolffd@0: selfprob = 0.1;
wolffd@0: 
wolffd@0: for i=1:2:length(varargin)
wolffd@0:   switch varargin{i},
wolffd@0:    case 'transprob', transprob = varargin{i+1}; 
wolffd@0:    case 'selfprob',  selfprob = varargin{i+1}; 
wolffd@0:    case 'startprob', startprob = varargin{i+1}; 
wolffd@0:    case 'startargs', startargs = varargin{i+1}; 
wolffd@0:    case 'transargs', transargs = varargin{i+1}; 
wolffd@0:    case 'F1toQ1',    CPD.F1toQ1 = varargin{i+1}; 
wolffd@0:   end
wolffd@0: end
wolffd@0: 
wolffd@0: Qps = CPD.Qps + ss;
wolffd@0: old_self = self-ss;
wolffd@0: 
wolffd@0: if strcmp(transprob, 'leftright')
wolffd@0:   LR = mk_leftright_transmat(Qsz, selfprob);
wolffd@0:   transprob = repmat(reshape(LR, [1 Qsz Qsz]), [Qpsz 1 1]); % transprob(k,i,j)
wolffd@0:   transprob = permute(transprob, [2 1 3]); % now transprob(i,k,j)
wolffd@0: end
wolffd@0: transargs{end+1} = 'CPT';
wolffd@0: transargs{end+1} = transprob;
wolffd@0: CPD.sub_CPD_trans = mk_isolated_tabular_CPD([old_self Qps], ns([old_self Qps self]), transargs);
wolffd@0: S = struct(CPD.sub_CPD_trans);
wolffd@0: CPD.transprob = myreshape(S.CPT, [Qsz Qpsz Qsz]);
wolffd@0: 
wolffd@0: 
wolffd@0: if strcmp(startprob, 'leftstart')
wolffd@0:   startprob = zeros(Qpsz, Qsz);
wolffd@0:   startprob(:,1) = 1;
wolffd@0: end
wolffd@0: 
wolffd@0: if (d==1) & ~CPD.F1toQ1
wolffd@0:   CPD.sub_CPD_start = [];
wolffd@0:   CPD.startprob = [];
wolffd@0: else
wolffd@0:   startargs{end+1} = 'CPT';
wolffd@0:   startargs{end+1} = startprob;
wolffd@0:   CPD.sub_CPD_start = mk_isolated_tabular_CPD(Qps, ns([Qps self]), startargs);
wolffd@0:   S = struct(CPD.sub_CPD_start);
wolffd@0:   CPD.startprob = myreshape(S.CPT, [Qpsz Qsz]);
wolffd@0: end
wolffd@0: 
wolffd@0: CPD = class(CPD, 'hhmmQ_CPD', tabular_CPD(bnet, self));
wolffd@0: 
wolffd@0: CPD = update_CPT(CPD);
wolffd@0: