Created using Colaboratory

Author: aamini

lab3/solutions/Lab3_Part_1_Introduction_to_CAPSA.ipynb

@@ -117,7 +117,7 @@
       "source": [
         "## 1.1 Dataset\n",
         "\n",
-        "We will build understanding of bias and uncertainty by training a neural network for a simple 2D regression task: modeling the function $y = x^3$. We will use `CAPSA` to analyze this dataset and the performance of the model. Noise and missing-ness will be injected into the dataset.\n",
+        "We will build understanding of bias and uncertainty by training a neural network for a simple 2D regression task: modeling the function $y = x^3$. We will use Capsa to analyze this dataset and the performance of the model. Noise and missing-ness will be injected into the dataset.\n",
         "\n",
         "Let's generate the dataset and visualize it:"
       ]
@@ -131,6 +131,7 @@
       "outputs": [],
       "source": [
         "# Get the data for the cubic function, injected with noise and missing-ness\n",
+        "# This is just a toy dataset that we can use to test some of the wrappers on\n",
         "def gen_data(x_min, x_max, n, train=True):\n",
         "  if train: \n",
         "    x = np.random.triangular(x_min, 2, x_max, size=(n, 1))\n",
@@ -211,7 +212,7 @@
         ")\n",
         "\n",
         "# Train the model for 30 epochs using model.fit().\n",
-        "loss_history = dense_NN.fit(x_train, y_train, epochs=30, verbose=0)"
+        "loss_history = dense_NN.fit(x_train, y_train, epochs=30)"
       ]
     },
     {
@@ -319,7 +320,7 @@
         ")\n",
         "\n",
         "# Train the wrapped model for 30 epochs.\n",
-        "loss_history_bias_wrap = bias_wrapped_dense_NN.fit(x_train, y_train, epochs=30, verbose=0)\n",
+        "loss_history_bias_wrap = bias_wrapped_dense_NN.fit(x_train, y_train, epochs=30)\n",
         "\n",
         "print(\"Done training model with Bias Wrapper!\")"
       ]