W1d2 postfixes (#531)

* minor fixes text * minor fix in latex * minor fix * minor fixes * minor fixes * Process tutorial notebooks Co-authored-by: GitHub Action <action@github.com>
NeuromatchAcademy · Dec 24, 2021 · 1091287 · 1091287
1 parent fd7fea1
commit 1091287
Show file tree

Hide file tree

Showing 12 changed files with 192 additions and 146 deletions.
diff --git a/tutorials/W1D1_BasicsAndPytorch/W1D1_Tutorial1.ipynb b/tutorials/W1D1_BasicsAndPytorch/W1D1_Tutorial1.ipynb
@@ -726,9 +726,13 @@
     "$B:$ a tensor with elements equal to the elements of numpy array $Z$\n",
     "\n",
     "$C:$ a tensor with the same number of elements as $A$ but with values $\n",
-    "\\sim U(0,1)$\n",
+    "\\sim \\mathcal{U}(0,1)^\\dagger$\n",
     "\n",
-    "$D:$ a 1D tensor containing the even numbers between 4 and 40 inclusive.\n"
+    "$D:$ a 1D tensor containing the even numbers between 4 and 40 inclusive.\n",
+    "\n",
+    "<br>\n",
+    "\n",
+    "$^\\dagger$: $\\mathcal{U(\\alpha, \\beta)}$ denotes the [uniform distribution](https://en.wikipedia.org/wiki/Continuous_uniform_distribution) from $\\alpha$ to $\\beta$, with $\\alpha, \\beta \\in \\mathbb{R}$.\n"
    ]
   },
   {
@@ -2945,24 +2949,25 @@
     "\n",
     "PyTorch provides a base class for all neural network modules called [`nn.Module`](https://pytorch.org/docs/stable/generated/torch.nn.Module.html). You need to inherit from `nn.Module` and implement some important methods:\n",
     "\n",
-    "`__init__`\n",
+    "* `__init__`\n",
     "\n",
-    "In the `__init__` method you need to define the structure of your network. Here you will specify what layers will the network consist of, what activation functions will be used etc.\n",
+    "  In the `__init__` method you need to define the structure of your network. Here you will specify what layers will the network consist of, what activation functions will be used etc.\n",
     "\n",
-    "`forward`\n",
+    "* `forward`\n",
     "\n",
-    "All neural network modules need to implement the `forward` method. It specifies the computations the network needs to do when data is passed through it.\n",
+    "  All neural network modules need to implement the `forward` method. It specifies the computations the network needs to do when data is passed through it.\n",
     "\n",
-    "`predict`\n",
+    "* `predict`\n",
     "\n",
-    "This is not an obligatory method of a neural network module, but it is a good practice if you want to quickly get the most likely label from the network. It calls the `forward` method and chooses the label with the highest score.\n",
+    "  This is not an obligatory method of a neural network module, but it is a good practice if you want to quickly get the most likely label from the network. It calls the `forward` method and chooses the label with the highest score.\n",
     "\n",
-    "`train`\n",
+    "* `train`\n",
     "\n",
-    "This is also not an obligatory method, but it is a good practice to have. The method will be used to train the network parameters and will be implemented later in the notebook.\n",
+    "  This is also not an obligatory method, but it is a good practice to have. The method will be used to train the network parameters and will be implemented later in the notebook.\n",
     "\n",
+    "<br>\n",
     "\n",
-    "> Note that you can use the `__call__` method of a module directly and it will invoke the `forward` method: `net()` does the same as `net.forward()`."
+    "**Note:** You can use the `__call__` method of a module directly and it will invoke the `forward` method: `net()` does the same as `net.forward()`."
    ]
   },
   {
@@ -3310,7 +3315,7 @@
    "outputs": [],
    "source": [
     "# @title Visualize the training process\n",
-    "# @markdown ### Execute this cell!\n",
+    "# @markdown Execute this cell!\n",
     "!pip install imageio --quiet\n",
     "!pip install pathlib --quiet\n",
     "\n",
@@ -3487,7 +3492,7 @@
    },
    "outputs": [],
    "source": [
-    "# @markdown ###Play with the parameters to solve XOR\n",
+    "# @markdown Play with the parameters to solve XOR\n",
     "from IPython.display import IFrame\n",
     "IFrame(\"https://playground.arashash.com/#activation=relu&batchSize=10&dataset=xor&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=&seed=0.91390&showTestData=false&discretize=false&percTrainData=90&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false\", width=1020, height=660)"
    ]

diff --git a/tutorials/W1D1_BasicsAndPytorch/student/W1D1_Tutorial1.ipynb b/tutorials/W1D1_BasicsAndPytorch/student/W1D1_Tutorial1.ipynb
@@ -726,9 +726,13 @@
     "$B:$ a tensor with elements equal to the elements of numpy array $Z$\n",
     "\n",
     "$C:$ a tensor with the same number of elements as $A$ but with values $\n",
-    "\\sim U(0,1)$\n",
+    "\\sim \\mathcal{U}(0,1)^\\dagger$\n",
     "\n",
-    "$D:$ a 1D tensor containing the even numbers between 4 and 40 inclusive.\n"
+    "$D:$ a 1D tensor containing the even numbers between 4 and 40 inclusive.\n",
+    "\n",
+    "<br>\n",
+    "\n",
+    "$^\\dagger$: $\\mathcal{U(\\alpha, \\beta)}$ denotes the [uniform distribution](https://en.wikipedia.org/wiki/Continuous_uniform_distribution) from $\\alpha$ to $\\beta$, with $\\alpha, \\beta \\in \\mathbb{R}$.\n"
    ]
   },
   {
@@ -2756,24 +2760,25 @@
     "\n",
     "PyTorch provides a base class for all neural network modules called [`nn.Module`](https://pytorch.org/docs/stable/generated/torch.nn.Module.html). You need to inherit from `nn.Module` and implement some important methods:\n",
     "\n",
-    "`__init__`\n",
+    "* `__init__`\n",
     "\n",
-    "In the `__init__` method you need to define the structure of your network. Here you will specify what layers will the network consist of, what activation functions will be used etc.\n",
+    "  In the `__init__` method you need to define the structure of your network. Here you will specify what layers will the network consist of, what activation functions will be used etc.\n",
     "\n",
-    "`forward`\n",
+    "* `forward`\n",
     "\n",
-    "All neural network modules need to implement the `forward` method. It specifies the computations the network needs to do when data is passed through it.\n",
+    "  All neural network modules need to implement the `forward` method. It specifies the computations the network needs to do when data is passed through it.\n",
     "\n",
-    "`predict`\n",
+    "* `predict`\n",
     "\n",
-    "This is not an obligatory method of a neural network module, but it is a good practice if you want to quickly get the most likely label from the network. It calls the `forward` method and chooses the label with the highest score.\n",
+    "  This is not an obligatory method of a neural network module, but it is a good practice if you want to quickly get the most likely label from the network. It calls the `forward` method and chooses the label with the highest score.\n",
     "\n",
-    "`train`\n",
+    "* `train`\n",
     "\n",
-    "This is also not an obligatory method, but it is a good practice to have. The method will be used to train the network parameters and will be implemented later in the notebook.\n",
+    "  This is also not an obligatory method, but it is a good practice to have. The method will be used to train the network parameters and will be implemented later in the notebook.\n",
     "\n",
+    "<br>\n",
     "\n",
-    "> Note that you can use the `__call__` method of a module directly and it will invoke the `forward` method: `net()` does the same as `net.forward()`."
+    "**Note:** You can use the `__call__` method of a module directly and it will invoke the `forward` method: `net()` does the same as `net.forward()`."
    ]
   },
   {
@@ -3110,7 +3115,7 @@
    "outputs": [],
    "source": [
     "# @title Visualize the training process\n",
-    "# @markdown ### Execute this cell!\n",
+    "# @markdown Execute this cell!\n",
     "!pip install imageio --quiet\n",
     "!pip install pathlib --quiet\n",
     "\n",
@@ -3287,7 +3292,7 @@
    },
    "outputs": [],
    "source": [
-    "# @markdown ###Play with the parameters to solve XOR\n",
+    "# @markdown Play with the parameters to solve XOR\n",
     "from IPython.display import IFrame\n",
     "IFrame(\"https://playground.arashash.com/#activation=relu&batchSize=10&dataset=xor&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=&seed=0.91390&showTestData=false&discretize=false&percTrainData=90&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false\", width=1020, height=660)"
    ]