Add table of content to nnet doc.

doc/library/tensor/nnet/nnet.txt

@@ -4,11 +4,23 @@
 :mod:`nnet` -- Ops for neural networks
 ======================================================
 
-.. module:: nnet
+.. module:: tensor.nnet
    :platform: Unix, Windows
    :synopsis: Ops for neural networks
 .. moduleauthor:: LISA
 
+
+- Sigmoid
+   - :func:`sigmoid`
+   - :func:`ultra_fast_sigmoid`
+   - :func:`hard_sigmoid`
+
+- Others
+   - :func:`softplus`
+   - :func:`softmax`
+   - :func:`binary_crossentropy`
+   - :func:`.categorical_crossentropy`
+
 .. function:: sigmoid(x)
 
    Returns the standard sigmoid nonlinearity applied to x
@@ -72,6 +84,7 @@
    .. note:: The underlying code will return an exact 0 or 1 if an
       element of x is too small or too big.
 
+
 .. function:: softplus(x)
 
    Returns the softplus nonlinearity applied to x