fixed minor typo (past tense verb) (#188)

notebooks/3_NeuralNetworks/autoencoder.ipynb

@@ -25,7 +25,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/bidirectional_rnn.ipynb

@@ -27,7 +27,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/convolutional_network.ipynb

@@ -25,7 +25,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/convolutional_network_raw.ipynb

@@ -24,7 +24,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/dcgan.ipynb

@@ -29,7 +29,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/gan.ipynb

@@ -31,7 +31,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/neural_network.ipynb

@@ -24,7 +24,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/neural_network_raw.ipynb

@@ -24,7 +24,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/recurrent_network.ipynb

@@ -27,7 +27,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",

notebooks/3_NeuralNetworks/variational_autoencoder.ipynb

@@ -31,7 +31,7 @@
     "\n",
     "## MNIST Dataset Overview\n",
     "\n",
-    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flatten and converted to a 1-D numpy array of 784 features (28*28).\n",
+    "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
     "\n",
     "![MNIST Dataset](http://neuralnetworksanddeeplearning.com/images/mnist_100_digits.png)\n",
     "\n",