{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "view-in-github",
    "colab_type": "text"
   },
   "source": [
    "<a href=\"https://colab.research.google.com/github/ebatty/MathToolsforNeuroscience/blob/jupyterbook/Week12/Video122.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "r-xn3WLqP2wM"
   },
   "source": [
    "# Video 12.2: Training Neural Networks"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "T9ckFFHNP2wQ"
   },
   "source": [
    "## Video"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "fTCqwicVP2wQ",
    "cellView": "form",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 449
    },
    "outputId": "2351c456-20fd-4195-c233-96445d0a12a0",
    "tags": [
     "remove-input"
    ]
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Video available at https://youtube.com/watch?v=DI3FrGDA27g\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x7f5aa845e890>"
      ],
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"730\"\n",
       "            height=\"410\"\n",
       "            src=\"https://www.youtube.com/embed/DI3FrGDA27g?fs=1\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "image/jpeg": "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\n"
     },
     "metadata": {},
     "execution_count": 1
    }
   ],
   "source": [
    "# @markdown\n",
    "from IPython.display import YouTubeVideo\n",
    "from ipywidgets import widgets\n",
    "out = widgets.Output()\n",
    "with out:\n",
    "    display(YouTubeVideo(id=f\"DI3FrGDA27g\", width=730, height=410, fs=1))\n",
    "display(out)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XMhhhdFCP2wS"
   },
   "source": [
    "## Notes\n",
    "\n",
    "<a href=\"https://osf.io/5a6kz/download\">\n",
    "    Click here to download notes\n",
    "</a>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "<img src=\"https://github.com/ebatty/MathToolsforNeuroscience/blob/jupyterbook/Week12/video12_2_notes.png?raw=True\" alt=\"notes for the video\" class=\"bg-primary\" width=\"100%\">"
   ],
   "metadata": {
    "id": "ZLDbFTdEcINM"
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.13 ('mathtools')",
   "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": "3.8.13"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "2f26a17d6a9624f855b5f9e02ffdc0ae71c8577a2562f495dada4b6f29d8bdd3"
   }
  },
  "colab": {
   "provenance": [],
   "include_colab_link": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}