Expend doc for softmax.

doc/library/tensor/nnet/nnet.txt

@@ -116,6 +116,20 @@
 
    The softmax function will, when applied to a matrix, compute the softmax values row-wise.
 
+    :note: this insert a particular op. But this op don't yet
+       implement the Rop for hessian free. If you want that, implement
+       this equivalent code that have the Rop implemented
+       ``exp(x)/exp(x).sum(1, keep_dims=True)``. Theano should
+       optimize this by inserting the softmax op itself.  The code of
+       the softmax op is more numeriacaly stable by using this code:
+
+       .. code-block:: python
+
+           e_x = exp(x - x.max(axis=1, keep_dims=True))
+           out = e_x / e_x.sum(axis=1, keep_dims=True)
+
+   Example of use:
+
    .. code-block:: python
 
        x,y,b = T.dvectors('x','y','b')