week41 exercises small changes

doc/LectureNotes/_build/jupyter_execute/.venv/lib/python3.13/site-packages/jupyter_book/book_template/markdown-notebooks.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "da3b753e",
+   "id": "1232311e",
    "metadata": {},
    "source": [
     "# Notebooks with MyST Markdown\n",
@@ -19,7 +19,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2bea4705",
+   "id": "f961e284",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1d36b822",
+   "id": "3b5f5a93",
    "metadata": {},
    "source": [
     "When your book is built, the contents of any `{code-cell}` blocks will be\n",

doc/LectureNotes/_build/jupyter_execute/exercisesweek41.ipynb

@@ -327,7 +327,7 @@
    "id": "0da7fd52",
    "metadata": {},
    "source": [
-    "**d)** Why is a neural network with no activation functions always mathematically equivelent to a neural network with only one layer?\n"
+    "**d)** Why is a neural network with no activation functions mathematically equivelent to(can be reduced to) a neural network with only one layer?\n"
    ]
   },
   {
@@ -454,7 +454,7 @@
    "id": "a6349db6",
    "metadata": {},
    "source": [
-    "**b)** Make a matrix of inputs with the shape (number of features, number of inputs), you choose the number of inputs and features per input. Then complete the function `feed_forward_batch` so that you can process this matrix of inputs with only one matrix multiplication and one broadcasted vector addition per layer. (Hint: You will only need to swap two variable around from your previous implementation, but remember to test that you get the same results for equivelent inputs!)\n"
+    "**b)** Make a matrix of inputs with the shape (number of inputs, number of features), you choose the number of inputs and features per input. Then complete the function `feed_forward_batch` so that you can process this matrix of inputs with only one matrix multiplication and one broadcasted vector addition per layer. (Hint: You will only need to swap two variable around from your previous implementation, but remember to test that you get the same results for equivelent inputs!)"
    ]
   },
   {
@@ -480,7 +480,7 @@
    "id": "efd07b4e",
    "metadata": {},
    "source": [
-    "**c)** Create and evaluate a neural network with 4 inputs and layers with output sizes 12, 10, 3 and activations ReLU, ReLU, softmax.\n"
+    "**c)** Create and evaluate a neural network with 4 input features, and layers with output sizes 12, 10, 3 and activations ReLU, ReLU, softmax.\n"
    ]
   },
   {