diff --git a/exercises/Jupyter notebook CVML.ipynb b/exercises/Jupyter notebook CVML.ipynb
index f2b45d5..e6022e5 100644
--- a/exercises/Jupyter notebook CVML.ipynb	
+++ b/exercises/Jupyter notebook CVML.ipynb	
@@ -2627,6 +2627,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "\"\"\"\n",
+    "compile het model met de binary crossentropy loss function. Dit doen we omdat\n",
+    "we maar 2 verschillende klassen hebben.\n",
+    "We gebruiken rmsprop als optimizer omdat INVULLEN\n",
+    "We gebruiken de accuracy als metric omdat we daarop willen trainen.\n",
+    "\"\"\"\n",
+    "\n",
     "model.compile(loss='binary_crossentropy',\n",
     "             optimizer='rmsprop',\n",
     "             metrics=['accuracy'])"
@@ -2792,6 +2799,9 @@
     }
    ],
    "source": [
+    "\n",
+    "#fit het model met de datasets. We gebruiken 70 epochs en 3 stappen per epoch.\n",
+    "\n",
     "model_ft = model.fit(train_dataset,\n",
     "                    steps_per_epoch=3,\n",
     "                    epochs=70,\n",
@@ -3188,6 +3198,7 @@
     }
    ],
    "source": [
+    "# laat het netwerk een prediction doen op alle test fotos.\n",
     "dir_path = '../data/imgs/test/'\n",
     "\n",
     "for i in os.listdir(dir_path):\n",
@@ -3210,12 +3221,13 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "530bae52",
+   "cell_type": "markdown",
+   "id": "069341a9",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "### Conclusie\n",
+    "We hebben het CNN getest en "
+   ]
   }
  ],
  "metadata": {