Fix doc indentation. They are part of their section, not at the global scope.

doc/library/tensor/nnet/nnet.txt

@@ -79,9 +79,9 @@
     :Return type: same as x
     :Returns: elementwise softplus: :math:`softplus(x) = \log_e{\left(1 + \exp(x)\right)}`.
 
-.. note:: The underlying code will return an exact 0 if an element of x is too small.
+   .. note:: The underlying code will return an exact 0 if an element of x is too small.
 
-.. code-block:: python
+   .. code-block:: python
 
        x,y,b = T.dvectors('x','y','b')
        W = T.dmatrix('W')
@@ -94,9 +94,9 @@
     :Return type: same as x
     :Returns: a symbolic 2D tensor whose ijth element is  :math:`softmax_{ij}(x) = \frac{\exp{x_{ij}}}{\sum_k\exp(x_{ik})}`.
 
-The softmax function will, when applied to a matrix, compute the softmax values row-wise. 
+   The softmax function will, when applied to a matrix, compute the softmax values row-wise.
 
-.. code-block:: python
+   .. code-block:: python
 
        x,y,b = T.dvectors('x','y','b')
        W = T.dmatrix('W')
@@ -113,12 +113,12 @@ The softmax function will, when applied to a matrix, compute the softmax values
     :Return type: same as target
     :Returns: a symbolic tensor, where the following is applied elementwise :math:`crossentropy(t,o) = -(t\cdot log(o) + (1 - t) \cdot log(1 - o))`.
 
-The following block implements a simple auto-associator with a sigmoid
-nonlinearity and a reconstruction error which corresponds to the binary
-cross-entropy (note that this assumes that x will contain values between 0 and
-1):
+   The following block implements a simple auto-associator with a
+   sigmoid nonlinearity and a reconstruction error which corresponds
+   to the binary cross-entropy (note that this assumes that x will
+   contain values between 0 and 1):
 
-.. code-block:: python
+   .. code-block:: python
 
        x, y, b = T.dvectors('x', 'y', 'b')
        W = T.dmatrix('W')
@@ -145,14 +145,16 @@ cross-entropy (note that this assumes that x will contain values between 0 and
 
     :Return type: tensor of rank one-less-than `coding_dist`
 
-.. note:: An application of the scenario where *true_dist* has a 1-of-N representation
-    is in classification with softmax outputs. If `coding_dist` is the output of
-    the softmax and `true_dist` is a vector of correct labels, then the function
-    will compute ``y_i = - \log(coding_dist[i, one_of_n[i]])``, which corresponds
-    to computing the neg-log-probability of the correct class (which is typically
-    the training criterion in classification settings).
+   .. note:: An application of the scenario where *true_dist* has a
+       1-of-N representation is in classification with softmax
+       outputs. If `coding_dist` is the output of the softmax and
+       `true_dist` is a vector of correct labels, then the function
+       will compute ``y_i = - \log(coding_dist[i, one_of_n[i]])``,
+       which corresponds to computing the neg-log-probability of the
+       correct class (which is typically the training criterion in
+       classification settings).
 
-.. code-block:: python
+   .. code-block:: python
 
        y = T.nnet.softmax(T.dot(W, x) + b)
        cost = T.nnet.categorical_crossentropy(y, o)