diff --git a/doc/HandWrittenNotes/NotesOctober1.pdf b/doc/HandWrittenNotes/NotesOctober1.pdf
new file mode 100644
index 000000000..7e30cc173
Binary files /dev/null and b/doc/HandWrittenNotes/NotesOctober1.pdf differ
diff --git a/doc/pub/week40/ipynb/week40.ipynb b/doc/pub/week40/ipynb/week40.ipynb
index fa3937386..40cdaefca 100644
--- a/doc/pub/week40/ipynb/week40.ipynb
+++ b/doc/pub/week40/ipynb/week40.ipynb
@@ -142,9 +142,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import numpy as np \n",
@@ -206,9 +204,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import numpy as np \n",
@@ -246,11 +242,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Own inversion\n",
+      "[[3.86030499]\n",
+      " [3.07504607]]\n",
+      "sgdreg from scikit\n",
+      "[3.85604957] [3.10480673]\n",
+      "theta from own gd\n",
+      "[[3.86030499]\n",
+      " [3.07504607]]\n",
+      "theta from own sdg\n",
+      "[[3.82144658]\n",
+      " [3.04835654]]\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "%matplotlib inline\n",
     "\n",
@@ -804,9 +828,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -862,9 +884,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -900,9 +920,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -953,9 +971,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -995,9 +1011,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1029,9 +1043,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1090,9 +1102,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1116,9 +1126,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1165,9 +1173,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1195,9 +1201,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1225,9 +1229,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import autograd.numpy as np\n",
@@ -1257,9 +1259,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "a += b\n",
@@ -1852,9 +1852,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "\"\"\"The sigmoid function (or the logistic curve) is a \n",
@@ -2562,7 +2560,25 @@
    ]
   }
  ],
- "metadata": {},
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 4
 }