Add a note about the implementation that will be used.

theano/tensor/nnet/abstract_conv.py

@@ -159,6 +159,11 @@ def conv2d(input,
     :rtype: symbolic 4D tensor
     :return: set of feature maps generated by convolutional layer. Tensor is
         of shape (batch size, output channels, output rows, output columns)
+
+    :note: If CuDNN is available, it will be used on the
+        GPU. Otherwise, it is the *CorrMM* convolution that will be used
+        "caffe style convolution".
+
     """
 
     conv_op = AbstractConv2d(imshp=input_shape,