diff --git a/lab2/Part2_FaceDetection.ipynb b/lab2/Part2_FaceDetection.ipynb
index c877149c..fc4c2333 100644
--- a/lab2/Part2_FaceDetection.ipynb
+++ b/lab2/Part2_FaceDetection.ipynb
@@ -515,7 +515,7 @@
       "source": [
         "## 2.5 Semi-supervised variational autoencoder (SS-VAE)\n",
         "\n",
-        "Now, we will use the general idea behind the VAE architecture to build a model to automatically uncover (potentially) unknown biases present within the training data, while simultaneously learning the facial detection task. This draws direct inspiration from [a recent paper](http://introtodeeplearning.com/AAAI_MitigatingAlgorithmicBias.pdf) proposing this as a general approach for automatic bias detetion and mitigation.\n"
+        "Now, we will use the general idea behind the VAE architecture to build a model to automatically uncover (potentially) unknown biases present within the training data, while simultaneously learning the facial detection task. This draws direct inspiration from [a recent paper](http://introtodeeplearning.com/AAAI_MitigatingAlgorithmicBias.pdf) proposing this as a general approach for automatic bias detection and mitigation.\n"
       ]
     },
     {
@@ -638,7 +638,7 @@
         "  # Build the decoder network using the Sequential API\n",
         "  decoder = tf.keras.Sequential([\n",
         "    # Transform to pre-convolutional generation\n",
-        "    Dense(units=4*4*6*n_filters),  # 4x4 feature maps (with 6N occurances)\n",
+        "    Dense(units=4*4*6*n_filters),  # 4x4 feature maps (with 6N occurences)\n",
         "    Reshape(target_shape=(4, 4, 6*n_filters)),\n",
         "\n",
         "    # Upscaling convolutions (inverse of encoder)\n",