diff --git a/docs/tutorials/research_tools.ipynb b/docs/tutorials/research_tools.ipynb
index fcb39d3c4..e388e0f9a 100644
--- a/docs/tutorials/research_tools.ipynb
+++ b/docs/tutorials/research_tools.ipynb
@@ -71,7 +71,7 @@
     "TensorFlow Quantum brings quantum primitives into the TensorFlow ecosystem. Now quantum researchers can leverage tools from TensorFlow. In this tutorial you will take a closer look at incorporating [TensorBoard](https://www.tensorflow.org/tensorboard) into your quantum computing research. Using the [DCGAN tutorial](https://www.tensorflow.org/tutorials/generative/dcgan) from TensorFlow you will quickly build up working experiments and visualizations similar to ones done by [Niu et al.](https://arxiv.org/pdf/2010.11983.pdf). Broadly speaking you will:\n",
     "\n",
     "1. Train a GAN to produce samples that look like they came from quantum circuits.\n",
-    "2. Visualize the training progress as well as distribuion evolution over time.\n",
+    "2. Visualize the training progress as well as distribution evolution over time.\n",
     "3. Benchmark the experiment by exploring the compute graph."
    ]
   },
@@ -356,7 +356,7 @@
     "\n",
     "\n",
     "def make_discriminator_model():\n",
-    "    \"\"\"Constrcut discriminator model.\"\"\"\n",
+    "    \"\"\"Construct discriminator model.\"\"\"\n",
     "    model = tf.keras.Sequential()\n",
     "    model.add(layers.Dense(256, use_bias=False, input_shape=(N_QUBITS,)))\n",
     "    model.add(layers.Dense(128, activation='relu'))\n",
@@ -538,7 +538,7 @@
     "id": "4ceb5dc64798"
    },
    "source": [
-    "## 3. Vizualize training and performance\n",
+    "## 3. Visualize training and performance\n",
     "\n",
     "The TensorBoard dashboard can now be launched with:"
    ]
@@ -901,7 +901,7 @@
     "id": "0ab7afeef60f"
    },
    "source": [
-    "When calling `train` the TensoBoard dashboard will auto-update with all of the summary statistics given in the training loop."
+    "When calling `train` the TensorBoard dashboard will auto-update with all of the summary statistics given in the training loop."
    ]
   },
   {