Merge pull request tensorflow#1614 from tensorflow/vincentvanhoucke-t…

…ypo-2

Typo in 2_fullyconnected.ipynb

tensorflow/examples/udacity/2_fullyconnected.ipynb

@@ -410,7 +410,7 @@
       "source": [
         "Let's now switch to stochastic gradient descent training instead, which is much faster.\n",
         "\n",
-        "The graph will be similar, except that instead of holding all the training data into a constant node, we create a `Placeholder` node which will be fed actual data at every call of `sesion.run()`."
+        "The graph will be similar, except that instead of holding all the training data into a constant node, we create a `Placeholder` node which will be fed actual data at every call of `session.run()`."
       ]
     },
     {