update colab link

AI4EPS · Nov 25, 2024 · fd4577e · fd4577e
1 parent 272657a
commit fd4577e
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 5 deletions.
diff --git a/docs/exercises/09_neural_networks1.ipynb b/docs/exercises/09_neural_networks1.ipynb
@@ -8,8 +8,8 @@
    "source": [
     "## Regression and Classification with Neural Networks\n",
     "\n",
-    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/lectures/09_neural_networks1.ipynb\">\n",
-    "<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>  "
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/exercises/09_neural_networks1.ipynb\">\n",
+    "<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a> "
    ]
   },
   {

diff --git a/docs/exercises/10_neural_networks2.ipynb b/docs/exercises/10_neural_networks2.ipynb
@@ -9,7 +9,7 @@
     "<!-- # MNIST with SciKit-Learn and PyTroch -->\n",
     "# Neural Networks with PyTorch\n",
     "\n",
-    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/lectures/10_neural_networks2.ipynb\">\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/exercises/10_neural_networks2.ipynb\">\n",
     "<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>  \n"
    ]
   },

diff --git a/docs/exercises/11_neural_networks3.ipynb b/docs/exercises/11_neural_networks3.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Finetuning AlexNet for Volcanic Deformation Classification\n",
     "\n",
-    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/lectures/11_neural_networks3.ipynb\">\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/AI4EPS/EPS88_PyEarth/blob/master/docs/exercises/11_neural_networks3.ipynb\">\n",
     "<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>  \n",
     "\n",
     "**Note**: If you are running this in [a colab notebook](https://colab.research.google.com/github/skorch-dev/skorch/blob/master/notebooks/MNIST.ipynb), we recommend you enable a free GPU by going:\n",
@@ -414,7 +414,7 @@
     "The loss function needs to fulfil the following conditions:\n",
     "- it has a derivative\n",
     "- it is written as a function of the outputs of the network\n",
-    "- it can be written as an average $\\mathcal{L}(Y^N, Y^*) = \\frac{1}{n} \\sum_\\mathbf{y} \\mathcal{L}(\\mathbf{y}^N, \\mathbf{y}^*) $\n",
+    "- it can be written as an average $ \\mathcal{L}(Y^{N}, Y^{*}) = \\frac{1}{n} \\sum_{\\mathbf{y}} \\mathcal{L}(\\mathbf{y}^{N}, \\mathbf{y}^{*}) $\n",
     "\n",
     "\n",
     "The last condition exists because a network is trained, in general, with a set of samples at once, known as a batch. The aim of training the network is to achieve a loss equal to $0$ on the entire dataset, as such using the whole dataset at once to calculate the gradient would be ideal. Unfortunately, this is unfeasible on big datasets. For this reason, small batches that fit into memory are used instead. They provide a more accurate update for the weights than using one sample at a time, while not being too computationally and memory intensive. \n",