Update regression.ipynb

Added the Note, as suggested in by Mark in the comment, tensorflow/tensorflow#24342 (comment)

Author: rmothukuru

site/en/tutorials/keras/regression.ipynb

@@ -408,6 +408,8 @@
         "One reason this is important is because the features are multiplied by the model weights. So the scale of the outputs and the scale of the gradients are affected by the scale of the inputs. \n",
         "\n",
         "Although a model *might* converge without feature normalization, normalization makes training much more stable. "
+        "\n",
+        "Note: Please refer the [Guide](https://www.tensorflow.org/guide/keras/preprocessing_layers) and the [Tutorial](https://www.tensorflow.org/tutorials/structured_data/preprocessing_layers) for more details about `Pre-Processing`."
       ]
     },
     {