Update week7.ipynb

Author: mhjensen

doc/pub/week7/ipynb/week7.ipynb

@@ -3,9 +3,7 @@
   {
    "cell_type": "markdown",
    "id": "e00f1a44",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "<!-- HTML file automatically generated from DocOnce source (https://github.com/doconce/doconce/)\n",
     "doconce format html week7.do.txt --no_mako -->\n",
@@ -15,9 +13,7 @@
   {
    "cell_type": "markdown",
    "id": "0521f5b9",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "# Advanced machine learning and data analysis for the physical sciences\n",
     "**Morten Hjorth-Jensen**, Department of Physics and Center for Computing in Science Education, University of Oslo, Norway\n",
@@ -28,9 +24,7 @@
   {
    "cell_type": "markdown",
    "id": "794145b7",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Plans for the week of March 3-7\n",
     "\n",
@@ -56,9 +50,7 @@
   {
    "cell_type": "markdown",
    "id": "e5e42fd9",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## What is a recurrent NN?\n",
     "\n",
@@ -77,9 +69,7 @@
   {
    "cell_type": "markdown",
    "id": "8ea5b91a",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Why RNNs?\n",
     "\n",
@@ -99,9 +89,7 @@
   {
    "cell_type": "markdown",
    "id": "6dadec9c",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Basic layout,  [Figures from Sebastian Rashcka et al, Machine learning with Sickit-Learn and PyTorch](https://sebastianraschka.com/blog/2022/ml-pytorch-book.html)\n",
     "\n",
@@ -115,9 +103,7 @@
   {
    "cell_type": "markdown",
    "id": "f69c94e7",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail\n",
     "\n",
@@ -131,9 +117,7 @@
   {
    "cell_type": "markdown",
    "id": "3e66ff38",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 2\n",
     "\n",
@@ -147,9 +131,7 @@
   {
    "cell_type": "markdown",
    "id": "a485dcbf",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 3\n",
     "\n",
@@ -163,9 +145,7 @@
   {
    "cell_type": "markdown",
    "id": "ea3e2dd7",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 4\n",
     "\n",
@@ -179,9 +159,7 @@
   {
    "cell_type": "markdown",
    "id": "5eed88f5",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 5\n",
     "\n",
@@ -195,9 +173,7 @@
   {
    "cell_type": "markdown",
    "id": "f4dd3d82",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 6\n",
     "\n",
@@ -211,9 +187,7 @@
   {
    "cell_type": "markdown",
    "id": "f2f57990",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## RNNs in more detail, part 7\n",
     "\n",
@@ -227,9 +201,7 @@
   {
    "cell_type": "markdown",
    "id": "f86b6161",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Backpropagation through time\n",
     "\n",
@@ -248,9 +220,7 @@
   {
    "cell_type": "markdown",
    "id": "40adbc7d",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## The backward pass is linear\n",
     "\n",
@@ -267,9 +237,7 @@
   {
    "cell_type": "markdown",
    "id": "bc9082ba",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## The problem of exploding or vanishing gradients\n",
     "* What happens to the magnitude of the gradients as we backpropagate through many layers?\n",
@@ -292,9 +260,7 @@
   {
    "cell_type": "markdown",
    "id": "9f380618",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## The mathematics of RNNs, the basic architecture\n",
     "\n",
@@ -304,12 +270,10 @@
   {
    "cell_type": "markdown",
    "id": "2b6f4cbd",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Four effective ways to learn an RNN and preparing for next week\n",
-    "1. Long Short Term Memory Make the RNN out of little modules that are designed to remember values for a long time.\n",
+    "1. Long Short Term Memory Make the RNN out of little modules that are designed to remember values for a long time. We discuss this next week.\n",
     "\n",
     "2. Hessian Free Optimization: Deal with the vanishing gradients problem by using a fancy optimizer that can detect directions with a tiny gradient but even smaller curvature.\n",
     "\n",
@@ -321,9 +285,7 @@
   {
    "cell_type": "markdown",
    "id": "ba57c26d",
-   "metadata": {
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Long Short Term Memory (LSTM)\n",
     "\n",
@@ -343,7 +305,25 @@
    ]
   }
  ],
- "metadata": {},
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.15"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 5
 }