diff --git a/site/en/tutorials/keras/classification.ipynb b/site/en/tutorials/keras/classification.ipynb
index dee10f107c3..95211303281 100644
--- a/site/en/tutorials/keras/classification.ipynb
+++ b/site/en/tutorials/keras/classification.ipynb
@@ -333,7 +333,7 @@
         "id": "rd0A0Iu0CaWq"
       },
       "source": [
-        "And the test set contains 10,000 images labels:"
+        "And the test set contains 10,000 image labels:"
       ]
     },
     {
@@ -444,7 +444,7 @@
         "\n",
         "The basic building block of a neural network is the [*layer*](https://www.tensorflow.org/api_docs/python/tf/keras/layers). Layers extract representations from the data fed into them. Hopefully, these representations are meaningful for the problem at hand.\n",
         "\n",
-        "Most of deep learning consists of chaining together simple layers. Most layers, such as `tf.keras.layers.Dense`, have parameters that are learned during training."
+        "Most deep learning models consist of chaining together simple layers. Most layers, such as `tf.keras.layers.Dense`, have parameters that are learned during training."
       ]
     },
     {
@@ -529,6 +529,7 @@
       },
       "outputs": [],
       "source": [
+        "# Train the neural network model\n",
         "model.fit(train_images, train_labels, epochs=10)"
       ]
     },
@@ -677,7 +678,7 @@
         "id": "ygh2yYC972ne"
       },
       "source": [
-        "Define functions to graph the full set of 10 class predictions."
+        "Define functions to visualize the full set of 10 class predictions."
       ]
     },
     {
@@ -860,7 +861,7 @@
         "id": "EQ5wLTkcCaXY"
       },
       "source": [
-        "Now predict the correct label for this image:"
+        "Now predict the label for this image:"
       ]
     },
     {