New parameter learning options

The main change here is in the parameter learning methods.  The parameters that are learned at first (i.e., if there is no evidence) are the distributions that are found directly in the data. I had to create or significantly modify several BNT files for this.

If there is evidence, the parameters are learned using a Dirichlet prior. This only required a couple of small changes to the BNW parameter learning files.

1 files changed, 2 insertions, 1 deletions

diff --git a/sourcecodes/parameter_learning/drawFigure.m b/sourcecodes/parameter_learning/drawFigure.m
index 7da07a90..c48f5b2d 100644
--- a/sourcecodes/parameter_learning/drawFigure.m
+++ b/sourcecodes/parameter_learning/drawFigure.m
@@ -123,7 +123,8 @@ for i = 1:nnodes,
         fprintf(fileID,format,num_child(i),children(1,:));
     end
     
-    predict = marginal_nodes(engine,i);
+%    predict = marginal_nodes(engine,i);
+    predict = marginal_nodes_no_ev(bnet,engine,i);
     if bnet.node_sizes(i) ~= 1,
         for j = 1:bnet.node_sizes(i),
             %%%For discrete nodes, the state and the percent of that state