diff --git a/11_deep_learning.ipynb b/11_deep_learning.ipynb
index 90c320a..b4bc4b3 100644
--- a/11_deep_learning.ipynb
+++ b/11_deep_learning.ipynb
@@ -55,11 +55,13 @@
     "\n",
     "# Common imports\n",
     "import numpy as np\n",
-    "import numpy.random as rnd\n",
     "import os\n",
     "\n",
     "# to make this notebook's output stable across runs\n",
-    "rnd.seed(42)\n",
+    "def reset_graph(seed=42):\n",
+    "    tf.reset_default_graph()\n",
+    "    tf.set_random_seed(seed)\n",
+    "    np.random.seed(seed)\n",
     "\n",
     "# To plot pretty figures\n",
     "%matplotlib inline\n",
@@ -181,7 +183,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -281,7 +283,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")"
    ]
@@ -322,7 +324,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -540,7 +542,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")"
    ]
@@ -596,7 +598,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "import tensorflow as tf\n",
     "\n",
@@ -632,7 +634,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
     "training = tf.placeholder_with_default(False, shape=(), name='training')"
@@ -693,7 +695,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "batch_norm_momentum = 0.9\n",
     "\n",
@@ -886,7 +888,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -1070,7 +1072,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()"
+    "reset_graph()"
    ]
   },
   {
@@ -1336,7 +1338,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -1431,7 +1433,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_hidden4 = 20  # new layer\n",
     "n_outputs = 10  # new layer\n",
@@ -1517,7 +1519,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300 # reused\n",
@@ -1622,7 +1624,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 2\n",
     "n_hidden1 = 3"
@@ -1690,7 +1692,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 2\n",
     "n_hidden1 = 3\n",
@@ -1802,7 +1804,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300 # reused\n",
@@ -1904,7 +1906,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300 # reused\n",
@@ -2026,7 +2028,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300 # reused\n",
@@ -2104,7 +2106,7 @@
     "    h2_cache_test = sess.run(hidden2, feed_dict={X: mnist.test.images}) # not shown in the book\n",
     "\n",
     "    for epoch in range(n_epochs):\n",
-    "        shuffled_idx = rnd.permutation(mnist.train.num_examples)\n",
+    "        shuffled_idx = np.random.permutation(mnist.train.num_examples)\n",
     "        hidden2_batches = np.array_split(h2_cache[shuffled_idx], n_batches)\n",
     "        y_batches = np.array_split(mnist.train.labels[shuffled_idx], n_batches)\n",
     "        for hidden2_batch, y_batch in zip(hidden2_batches, y_batches):\n",
@@ -2265,7 +2267,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -2390,7 +2392,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -2518,7 +2520,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28  # MNIST\n",
     "n_hidden1 = 300\n",
@@ -2694,7 +2696,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "X = tf.placeholder(tf.float32, shape=(None, n_inputs), name=\"X\")\n",
     "y = tf.placeholder(tf.int64, shape=(None), name=\"y\")"
@@ -2807,7 +2809,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28\n",
     "n_hidden1 = 300\n",
@@ -3012,7 +3014,7 @@
    },
    "outputs": [],
    "source": [
-    "tf.reset_default_graph()\n",
+    "reset_graph()\n",
     "\n",
     "n_inputs = 28 * 28\n",
     "n_hidden1 = 300\n",