Make notebooks uniform, rename 'Learning Objectives'

Notebooks_EN/12 - Autoencoders.ipynb

@@ -10,11 +10,11 @@
     "\n",
     "#### I did my best to minimize the training time. I had saved a model that was trained already. However, the server does not play along. Therefore it is best to just do something else for an hour when training. You don't have to train 100 epochs, you can end the training early via Kernel > Interrupt Kernel.\n",
     "---\n",
-    "**Learning Objectives**\n",
-    "- You understand the concept of an autoencoder\n",
-    "- You understand the meaning of `<sos>`/`<eos>` tokens \n",
-    "- You understand how an RNN can generate Smiles\n",
-    "- You can also define a network as a PyTorch class\n",
+    "### In this lesson you'll learn:\n",
+    "- what an autoencoder is.\n",
+    "- the meaning of `<sos>`/`<eos>` tokens.\n",
+    "- how an RNN can generate SMILES.\n",
+    "- how to define a network as a PyTorch class.\n",
     "---\n",
     "\n",
     "In today's notebook we will deal with the so called **autoencoders**.\n",

Notebooks_EN/13 - Graph Neural Networks.ipynb

@@ -9,10 +9,11 @@
     "\n",
     "\n",
     "---\n",
-    "**Learning Objectives**\n",
-    "* You understand how molecules can be represented as graphs. \n",
-    "* You will understand how basic Graph Neural Networks work.\n",
-    "* You will be able to write a Graph Neural Network as a Pytorch class.\n",
+    "### In this lesson you'll learn:\n",
+    "\n",
+    "* how molecules can be represented as graphs. \n",
+    "* how basic Graph Neural Networks work.\n",
+    "* how to write a Graph Neural Network as a Pytorch class.\n",
     "---\n",
     "\n",
     "\n",

Notebooks_EN/14 - Summary.ipynb

@@ -8,9 +8,9 @@
     "# An overview\n",
     "\n",
     "---\n",
-    "Learning Objectives\n",
+    "### In this lesson you'll learn:\n",
     "\n",
-    "- You understand the relationship between a (logistic) regression and neural networks.\n",
+    "- to understand the relationship between a (logistic) regression and neural networks.\n",
     "---\n",
     "\n",
     "In this notebook we will have a last look at different model architectures and how they are related.\n",

Notebooks_GER/Woche 12 - Autoencoders.ipynb

@@ -10,10 +10,10 @@
     "#### Ich habe mein Bestes getan, um die Trainingszeit zu minimieren. Ich hatte ein bereits trainiertes Modell gespeichert. Allerdings spielt der Server nicht mit. Deswegen am besten beim Training einfach eine Stunde lang etwas anderes machen. Man muss nicht 100 Epochen trainieren, sondern kann das Training über Kernel > Interrupt Kernel vorzeitig beenden.\n",
     "---\n",
     "**Lernziele**\n",
-    "- Sie verstehen das Konzept eines Autoencoders\n",
-    "- Sie verstehen, wie ein RNN Smiles erzeugen kann\n",
-    "- Sie können ein Netzwerk auch als PyTorch-Class definieren\n",
-    "- Du verstehst die Bedeutung der `<sos>`/`<eos>`-Tokens \n",
+    "- Sie verstehen das Konzept eines Autoencoders.\n",
+    "- Sie verstehen, wie ein RNN SMILES erzeugen kann.\n",
+    "- Sie können ein Netzwerk auch als PyTorch-Class definieren.\n",
+    "- Sie verstehen die Bedeutung der `<sos>`/`<eos>`-Tokens.\n",
     "---\n",
     "\n",
     "Im heutigen Notebook beschäftigen wir uns mit den sogenannten **Autoencodern**.\n",

Notebooks_GER/Woche 14 - Zusammenfassung.ipynb

@@ -10,7 +10,7 @@
     "---\n",
     "Lernziel\n",
     "\n",
-    "- Sie verstehen, den Zusammenhang einer (logistischer) Regression und Neuronalen Netzwerken\n",
+    "- Sie verstehen den Zusammenhang einer (logistischer) Regression und Neuronalen Netzwerken.\n",
     "---\n",
     "\n",
     "Im letzten Notebook werden wir uns noch ein letztes Mal mit verschieden Netzwerk-Architekturen auseinandersetzen und wie diese zusammen hängen.\n",