Added explanation for the output

Author: gurumurthys

introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-fulltraining.ipynb

@@ -530,7 +530,8 @@
    "source": [
     "### Evaluation\n",
     "\n",
-    "Evaluate the image through the network for inteference. The network outputs class probabilities and we can select the class with the maximum probability as final class output. However, in this example, the output class may not be correct. This is because we have trained the model only for a couple of epochs. If the network is trained for more epochs (say 20), then the output class will be more accurate."
+    "Evaluate the image through the network for inteference. The network outputs class probabilities and typically, one selects the class with the maximum probability as the final class output.\n",
+    "**Note:** The output class detected by the network may not be accurate in this example. This is because we have trained the model only for a couple of epochs. If the network is trained for more epochs (say 20), then the output class will be more accurate."
    ]
   },
   {