diff --git a/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb b/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb
index daaa24ea..07aede9a 100644
--- a/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb
+++ b/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb
@@ -395,8 +395,8 @@
         "cumulative_headcounts = tf.gather(tf.cumsum(coin_flip_data), num_trials)\n",
         "\n",
         "rv_observed_heads = tfp.distributions.Beta(\n",
-        "    concentration1=tf.to_float(1 + cumulative_headcounts),\n",
-        "    concentration0=tf.to_float(1 + num_trials - cumulative_headcounts))\n",
+        "    concentration1=tf.cast(1 + cumulative_headcounts, tf.float32),\n",
+        "    concentration0=tf.cast(1 + num_trials - cumulative_headcounts, tf.float32))\n",
         "\n",
         "probs_of_heads = tf.linspace(start=0., stop=1., num=100, name=\"linspace\")\n",
         "observed_probs_heads = tf.transpose(rv_observed_heads.prob(probs_of_heads[:, tf.newaxis]))"
@@ -1207,8 +1207,8 @@
       "source": [
         "# Set the chain's start state.\n",
         "initial_chain_state = [\n",
-        "    tf.to_float(tf.reduce_mean(count_data)) * tf.ones([], dtype=tf.float32, name=\"init_lambda1\"),\n",
-        "    tf.to_float(tf.reduce_mean(count_data)) * tf.ones([], dtype=tf.float32, name=\"init_lambda2\"),\n",
+        "    tf.cast(tf.reduce_mean(count_data), tf.float32) * tf.ones([], dtype=tf.float32, name=\"init_lambda1\"),\n",
+        "    tf.cast(tf.reduce_mean(count_data), tf.float32) * tf.ones([], dtype=tf.float32, name=\"init_lambda2\", tf.float32),\n",
         "    0.5 * tf.ones([], dtype=tf.float32, name=\"init_tau\"),\n",
         "]\n",
         "\n",
@@ -1234,7 +1234,7 @@
         "\n",
         "    lambda_ = tf.gather(\n",
         "         [lambda_1, lambda_2],\n",
-        "         indices=tf.to_int32(tau * tf.to_float(tf.size(count_data)) <= tf.to_float(tf.range(tf.size(count_data)))))\n",
+        "         indices=tf.to_int32(tau * tf.cast(tf.size(count_data), tf.float32) <= tf.cast(tf.range(tf.size(count_data)), tf.float32)))\n",
         "    rv_observation = tfd.Poisson(rate=lambda_)\n",
         " \n",
         "    return (\n",
@@ -1277,7 +1277,7 @@
         "            state_gradients_are_stopped=True),\n",
         "        bijector=unconstraining_bijectors))\n",
         "\n",
-        "tau_samples = tf.floor(posterior_tau * tf.to_float(tf.size(count_data)))\n",
+        "tau_samples = tf.floor(posterior_tau * tf.cast(tf.size(count_data)), tf.float32)\n",
         "\n",
         "# tau_samples, lambda_1_samples, lambda_2_samples contain\n",
         "# N samples from the corresponding posterior distribution\n",
@@ -1644,4 +1644,4 @@
       ]
     }
   ]
-}
\ No newline at end of file
+}