Merge pull request #3750 from andreh7/ah-2015-12-05-more-comments-on-logistic-regression-example

doc/tutorial/examples.txt

@@ -489,16 +489,27 @@ It will be used repeatedly.
     import theano.tensor as T
     rng = numpy.random
   
-    N = 400
-    feats = 784
+    N = 400                                   # training sample size
+    feats = 784                               # number of input variables
+
+    # generate a dataset: D = (input_values, target_class)
     D = (rng.randn(N, feats), rng.randint(size=N, low=0, high=2))
     training_steps = 10000
   
     # Declare Theano symbolic variables
     x = T.matrix("x")
     y = T.vector("y")
+
+    # initialize the weight vector w randomly
+    #
+    # this and the following bias variable b
+    # are shared so they keep their values
+    # between training iterations (updates)
     w = theano.shared(rng.randn(feats), name="w")
+
+    # initialize the bias term
     b = theano.shared(0., name="b")
+
     print("Initial model:")
     print(w.get_value())
     print(b.get_value())
@@ -509,6 +520,8 @@ It will be used repeatedly.
     xent = -y * T.log(p_1) - (1-y) * T.log(1-p_1) # Cross-entropy loss function
     cost = xent.mean() + 0.01 * (w ** 2).sum()# The cost to minimize
     gw, gb = T.grad(cost, [w, b])             # Compute the gradient of the cost
+                                              # w.r.t weight vector w and
+                                              # bias term b
                                               # (we shall return to this in a
                                               # following section of this tutorial)