Merge branch 'master' of https://github.com/MicrosoftDocs/ml-basics

Author: GraemeMalcolm

05a - Deep Neural Networks (TensorFlow).ipynb

@@ -79,7 +79,7 @@
       "cell_type": "markdown",
       "source": [
         "### Prepare the Data for Tensorflow\n",
-        "We've already loaded our data and split it into training and validation datasets. However, we need to do some further data preparation so that our data will work correctly with Tensorflow. Specifically, we need to set the data type of our labels to 32-bit floating point numbers, and specify that the labels represent categorical classes rather than numeric values."
+        "We've already loaded our data and split it into training and validation datasets. However, we need to do some further data preparation so that our data will work correctly with Tensorflow. Specifically, we need to set the data type of our features to 32-bit floating point numbers, and specify that the labels represent categorical classes rather than numeric values."
       ]
     },
     {
@@ -137,7 +137,7 @@
         "### Train the Model\n",
         "To train the model, we need to repeatedly feed the training values forward through the network, use a loss function to calculate the loss, use an optimizer to backpropagate the weight and bias value adjustments, and validate the model using the test data we withheld.\n",
         "\n",
-        "To do this, we'll apply a Stochastic Gradient Descent optimizer to a categorical cross-entropy loss function iteratively over 100 epochs."
+        "To do this, we'll apply a Stochastic Gradient Descent optimizer to a categorical cross-entropy loss function iteratively over 50 epochs."
       ]
     },
     {
@@ -326,4 +326,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 2
-}
+}