update theano TUT

Author: Mofan Zhou

theanoTUT/theano7_activation_function.py

@@ -11,8 +11,8 @@
 
 The activation functions include but not limited to softplus, sigmoid, relu, softmax, elu, tanh...
 
-For the hidden layer, we could use relu, tanh...
-For classification problems, we could use softplus or softmax for the output layer.
+For the hidden layer, we could use relu, tanh, softplus...
+For classification problems, we could use sigmoid or softmax for the output layer.
 For regression problems, we could use a linear function for the output layer.
 
 """