diff --git a/doc/design/graph.md b/doc/design/graph.md
index 87f696f90f164a639ad5182823ddfb14aab7e065..e59d04e1f562ea754486aca5bfbf10fccd0f2326 100644
--- a/doc/design/graph.md
+++ b/doc/design/graph.md
@@ -25,7 +25,9 @@ The first four lines of above program build the forward part of the graph.
 
 ![](images/graph_construction_example_forward_only.png)
 
-In particular, the first line `x = layer.data("images")` creates variable x and a Feed operator that copies a column from the minibatch to x.  `y = layer.fc(x)` creates not only the FC operator and output variable y, but also two parameters, W and b.
+In particular, the first line `x = layer.data("images")` creates variable x and a Feed operator that copies a column from the minibatch to x.  `y = layer.fc(x)` creates not only the FC operator and output variable y, but also two parameters, W and b, and the initialization operators.
+
+Initialization operators are kind of "run-once" operators -- the `Run` method increments a class data member counter so to run at most once.  By doing so, a parameter wouldn't be initialized repeatedly, say, in every minibatch.
 
 In this example, all operators are created as `OpDesc` protobuf messages, and all variables are `VarDesc`.  These protobuf messages are saved in a `BlockDesc` protobuf message.
 
diff --git a/doc/design/images/graph_construction_example.dot b/doc/design/images/graph_construction_example.dot
index bedb6de0111a8ccab4030d034d65cf72705fc25a..8d1b673abf6b78c851676fa379dc850c4818f0e5 100644
--- a/doc/design/images/graph_construction_example.dot
+++ b/doc/design/images/graph_construction_example.dot
@@ -2,6 +2,8 @@ digraph ImageClassificationGraph {
         ///////// The forward part /////////
         FeedX [label="Feed", color=blue, shape=box];
         FeedY [label="Feed", color=blue, shape=box];
+        InitW [label="Init", color=blue, shape=diamond];
+        Initb [label="Init", color=blue, shape=diamond];
         FC [label="FC", color=blue, shape=box];
         MSE [label="MSE", color=blue, shape=box];
 
@@ -14,6 +16,8 @@ digraph ImageClassificationGraph {
 
         FeedX -> x -> FC -> y -> MSE -> cost [color=blue];
         FeedY -> l [color=blue];
+        InitW -> W [color=blue];
+        Initb -> b [color=blue];
         W -> FC [color=blue];
         b -> FC [color=blue];
         l -> MSE [color=blue];
diff --git a/doc/design/images/graph_construction_example_all.png b/doc/design/images/graph_construction_example_all.png
index 18d8330b60e12720bb993c8cf588d64ff8db1ea9..181187503472d15779b87284105841168b3945c4 100644
Binary files a/doc/design/images/graph_construction_example_all.png and b/doc/design/images/graph_construction_example_all.png differ
diff --git a/doc/design/images/graph_construction_example_forward_backward.png b/doc/design/images/graph_construction_example_forward_backward.png
index 61c3a02a04bc8891ab5b921a889829bcce386df8..3049a9315fd616464dec54e33064cb75598ca536 100644
Binary files a/doc/design/images/graph_construction_example_forward_backward.png and b/doc/design/images/graph_construction_example_forward_backward.png differ
diff --git a/doc/design/images/graph_construction_example_forward_only.png b/doc/design/images/graph_construction_example_forward_only.png
index 14805df11fc09f64d6bc17f5e969f1400d615148..25d19088cbf0b5f68cf734f2ff21eba8af4a2860 100644
Binary files a/doc/design/images/graph_construction_example_forward_only.png and b/doc/design/images/graph_construction_example_forward_only.png differ