umz21/wyk/01_Wprowadzenie.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Uczenie maszynowe – zastosowania\n",
    "# 1. Wprowadzenie"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## 1.1. Czym jest uczenie maszynowe?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"terms-cloud.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Sztuczna inteligencja (*artificial intelligence*)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Naśladowanie ludzkich procesów poznawczych za pomocą komputerów"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Konstruowanie systemów (maszyn), których działanie podobne jest do przejawów ludzkiej inteligencji"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Dziedzina nauki, która zajmuje się naśladowaniem ludzkiej inteligencji przez komputery"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Obejmuje m.in. logikę rozmytą, algorytmy ewolucyjne, robotykę i uczenie maszynowe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"venn-ai.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Uczenie maszynowe (*machine learning*)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Tworzenie systemów, które potrafią doskonalić się przy pomocy zgromadzonego doświadczenia"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"venn-ai-ml.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Sieci neuronowe (neural networks)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Rodzaj struktur matematycznych, które wykonują obliczenia przy pomocy elementów zwanych _sztucznymi neuronami_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Budowa sieci neuronowych i zasady działania sztucznych neuronów były luźno inspirowane działaniem neuronów w mózgu"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"venn-ai-ml-nn.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Uczenie głębokie (deep learning)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Użycie sieci neuronowych do automatycznego wydobywania cech z surowych danych"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"venn-ai-ml-nn-dl.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Data science"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* Dziedzina nauki zajmująca się przetwarzaniem danych w celu wydobycia z nich wiedzy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" src=\"venn-ai-ml-nn-dl-ds.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Uczenie maszynowe – klasyczne definicje"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"float: right;\" src=\"https://upload.wikimedia.org/wikipedia/commons/f/f8/This_is_the_photo_of_Arthur_Samuel.jpg\"/>\n",
    "\n",
    "> Uczenie maszynowe to dziedzina nauki,\n",
    "> która daje komputerom umiejętność uczenia się\n",
    "> bez programowania ich _explicite_.\n",
    "\n",
    "> &mdash; <cite>Arthur Samuel, 1959</cite>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"float: right;\" width=\"20%\" src=\"http://mediad.publicbroadcasting.net/p/wamc/files/styles/x_large/public/201401/tom_mitchell.jpg\"/>\n",
    "\n",
    "> Mówimy, że program komputerowy **uczy się**\n",
    "> z doświadczenia E w odniesieniu do zadania T i miary skuteczności P,\n",
    "> jeżeli jego skuteczność wykonywania zadania T mierzona według P\n",
    "> wzrasta z doświadczeniem E.\n",
    "\n",
    "> &mdash; <cite>Tom Mitchell, 1998</cite>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" width=\"40%\" src=\"https://static1.squarespace.com/static/5150aec6e4b0e340ec52710a/t/51525c33e4b0b3e0d10f77ab/1364352052403/Data_Science_VD.png\"/>\n",
    "\n",
    "<sub>Źródło: Drew Conway, http://drewconway.com/zia/2013/3/26/the-data-science-venn-diagram</sub>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "Uczenie maszynowe to:\n",
    "\n",
    "* doskonalenie działania dla pewnych zadań na podstawie doświadczenia"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* tworzenie systemów, które doskonalą swoje działania na podstawie przeszłych doświadczeń"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "* zestaw metod, które potrafią w sposób automatyczny wykrywać wzorce w danych, a następnie używać wcześniej niezaobserwowanych wzorców do przewidywania przyszłych zjawisk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "Charakterystyczne cechy uczenia maszynowego:\n",
    "\n",
    "* „automatyzacja automatyzacji”\n",
    "* komputer „sam się programuje”\n",
    "* modelowanie danych zastępuje pisanie programu"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "<img style=\"margin: auto\" width=\"80%\" src=\"https://recast.ai/blog/wp-content/uploads/2017/02/image20.png\"/>\n",
    "\n",
    "<sub>Źródło: https://recast.ai/blog/machine-learning-algorithms/</sub>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "slideshow": {
     "slide_type": "notes"
    }
   },
   "outputs": [],
   "source": [
    "import IPython"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/R9OHn5ZF4Uo\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c739370>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('R9OHn5ZF4Uo', width=800, height=600)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## 1.2. Zastosowania uczenia maszynowego"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/ahRcGObyEZo\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c739d30>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('ahRcGObyEZo', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/oLTNtvIHJ7M\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d070>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('oLTNtvIHJ7M', width=800, height=600)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "* rozpoznawanie i rozumienie mowy\n",
    "* rozpoznawanie obrazów\n",
    "* tłumaczenie maszynowe\n",
    "* systemy rekomendacyjne\n",
    "* detekcja spamu\n",
    "* klasyfikacja dokumentów/obrazów\n",
    "* analiza nastrojów\n",
    "* rozpoznawanie pisma odręcznego\n",
    "* samochody autonomiczne\n",
    "* przewidywanie kursów giełdowych\n",
    "* automatyczna diagnostyka medyczna\n",
    "* analiza genów\n",
    "* sztuczna inteligencja w grach"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Co potrafi uczenie maszynowe?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAUDBA0NDQ0NDQ0NDQ0NDQ0NDQ0NDQ0NDQ0NCA0ICAgIDQ0NDRANDQ0ODQgIDRUNDhERExMTCA0WGBYSGBASExIBBQUFCAcIDwkJDxYPDw8VFRUVFRUVFRUVFRUVFRUVFRUSFRUVFRIVFRUVFRUVEhUVFRUVEhUVFRUVEhUVFRUVFf/AABEIAWgB4AMBIgACEQEDEQH/xAAcAAABBQEBAQAAAAAAAAAAAAAAAgMEBQYBBwj/xABUEAABAwEFAgcIDgkDAgYDAQABAAIDEQQFEiExQVEGEyJhcYGRMlKSk6HR09QHFBUYI0JTVGJyscHS8AgWM0NjgpSi4Rckc7LxNER0g7PiZMLDJf/EABsBAQACAwEBAAAAAAAAAAAAAAABAgMEBQYH/8QANxEAAgEDAgMECgIBBQADAAAAAAECAwQREjEFIVETQVJhBhQVIjJCcYGRobHB8CNi0eHxQ1Oy/9oADAMBAAIRAxEAPwD4yQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQhCAEIQgBCEIAQt6fYptXyln8OT0S5/pXavlLP4UnolueoXHgZp+0LfxowaF6TH7Ct4FuICOm+svolDm9im1t7p0I6XSD/8AkoVjXe0SXfUFvJGCQtz/AKYWnv4PCk9EuH2MrT38HhSeiVvZ1x4GR7Qt/GjDoW2/0ztPfweFJ6Jc/wBNbT38HhSejT2dc+Bj2hb+NGKQtofY2tPfweFJ6NcPscWnv4fCf6NT7NufAx7Qt/GjGIWy/wBOrR38PhP9Guf6dWjv4fCf6NPZtz4GPaFv40Y5C2P+nlo7+Hwn+jXP9PbR38PhP9Gns258DHtC38aMeha8+x9aO/h8J/o1z/T+0d/D4T/Rp7NufAx7Qt/GjIoWu/UC0d/D4T/Rrn6gWjv4fCf6NPZtz4GPX7fxoySFrP1Bn7+Hwn+jR+oU/fw+E/0aezbnwMev2/jRk0LWfqFP38PhP9Gj9Qp+/i8J/o09m3PgY9ft/GjJoWr/AFDn7+Lwn+jR+oc/fxeE/wBGns258DHr9v40ZRC1f6hz9/F4T/Ro/UOfv4vCf6NPZtz4GPX7fxoyiFq/1Dn7+Lwn+jXf1Cn7+Lwn+jT2bc+Bj1+38aMmhaz9Qp+/h8J/o0fqDP38XhP9Gns258DHr9v40ZNC9JsvsJ3k9oe1kZacxynDrpgUyw+wJebzSkLOd73geSMlYXa1Fuv4MiuqT2Z5Uhe1t/RpvI/vrF4yf1ZPe9ivP5ew+NtHqqxdnLoZe0j1PDkL3D3sd5/L2Hxto9VST+jNefy1h8bP6snZy6DtI9TxFC9w97Hefy9h8baPVlHH6N94/LWLxk/qydnLoO1j1PF0L2g/o3Xj8tYvGT+rJEv6OV4j99YuqSf1ZOzl0I7WHU8aQvYHfo8XiNZbH4yb1dUd9+xBbIHBr5LOSRWrXykeWELJC2qTeIxyyk7mnBZk8I87Qtt/ppae/g8KT0S7/pnae/g8KT0SzezrnwMxe0LfxoxCFuP9MbT38HhSeiXf9MLT38HhSeiT2dceBj2hb+NGGQt0PYvtXfweFJ6JdHsW2rv4PCk9Ens648DI9o2/jRhELfs9ie1n95Z/Dk9En4/Ydth/eWbw5fQqrsK6+Rkq/t386POUL06P2Eraf3tl8OX0Ckx+wLbz+9snjJvQKrs6y+Vl1eUX8yPKEL2GP9Hi8D++sfjJ/V1Jj/RrvI/v7D4yf1ZUdvUXcXVxTezPFUL3OP8ARfvM/v7B420eqp9n6Kt6H/zF3+NtHqqo6cl3F1Ui+88FQvoBn6Jl6n/zF3+NtPqidb+iNe3zi7vHWn1RVwyyaPnpC+h/eh3v84u7x1p9TR70O9/nF3eOtPqagk0ccJcQ0ak0HSV65wP4ERwtDpAHyHPPMN5h51lPY8uFz5mSObyG1cCdpGnl+xestqvS8RunnRF/U8vw62WNcl9BHtdtKUVBe9zRvqHNDh0BacMTD4WrlKTXNHWcU1hnk3CDgKBV0Roe9P3LBTWdwJaQajIhfQlrswJy6E8LqhGeBpcdSQKrpUOJTgsT945tbh0ZvMfdPnAwncewppzF9HvuyPvG9g8ypb44E2eX4oa7e3IrbhxeLfvRwa8+FyS915PByxILV6NffsZysqYnB43HI9G5Yq8rskiOGRhaecLpUrqnU+F5NGpQnT+JYKstSS1SnMSC1bCZhIpC4WqQWJBYrZAwWpJany1JIQDBaklqkFq4WoSR6LlE+WrhYpGRjCuYU/gRgQZGMKMKewIwIMjOFGFPYEYUGRnCu4U7hShGgyMBq9N9i/gQHgWiYVHxGHbT45UHgVwAkmIklGCPI0PdO5qbAvZLPAGgNaKAAAAbhkFxOJX6S7Om+fezp2Vo29c1y7gDBsS2xFSIod6eBC8/g7WBMEVOlEj0mecAaqvltzRtV0g2T2uXSotmnqK6JRQgfdNuUcsS2oAUAa4qq5aoqDoUpoXSgKK1mq889k6zZxu6R969SnsAOY7FR8IeDwmbhcCKaEbCtq0rKnUUnsat1RdSm4rc8XaxLDVd33wekgOYq3Y4ffuVW1q9NCrGazF5POzjKDw1hjTWJYYnQxLaxTkx5GQxLaxPNYltYq5AqzsVlZWKLZ2KzsrFhmzLAnWRqt7I1V9kYreyNWlUZu0ixsjVcWQKtsjVbWQLQqM6FIsrKFaWYKusoVlZ1oVDoUydApsShwhTI1qTN2A6hCFjMhg4rAGUDcsIoOrJT2CqaM20JcTlu5ZzksCimJnUSpLS3vh2qvtN4sFc69ClINnWjNSSFRy34xpzIHSVJjvyM/HZ2q+h9CuuPUsuLS2soq33WYfjtHQUe6sffVUaWTqRZqp4TXPHaIy17Qdx2joKHXu3Z9qjy3x0K0dUXlFZaWsPY8m4RcDZoiS1pezYQMx0hZqSIjIih517yL6btLe0Kqv2Gx2hpDy1rtjhQEHq1XYt+JTXKaz5o5Fbh8d4P7M8XLEgsV5ft0iJ1A9r27C0/aFWFq7Eaikso5ck4vDIhYklilliSWLJkgiFiTgUosXCxTkETCuFqlmNJ4tEwRsK5hUri1zApyCNhRhUji0YEyBqCzudk1pcdwFVo7l4DWmahwYG98/LyaqosVofGcTHFp3hXx4a2ugHGafRC167rf8Ax4+5mpdn8+fsa26vYviAHGPc87hkPOtRdvA6zx5tibUbTmenNeSHhXavlXDsSDwmtXy7+1cypZ3NT4pm7C6oQ2ge+RMDdaJia9YgaYm16QvDrZwptUgDXSuoBTLKvSVUPkccy4k76lYocIl80jNLii+WJ9EOtze+Haok97MG0HrC8FbK/vndpRiO89pV1wj/AHfoo+Kf7f2e3Wy8sWgUAyLy6G9ZgKCR1OlNvtkh1e49ZULhjXeg+Jx6HuV0ykjmVi1oXhNgv20R9zI7oOYU9vC609/XqWGXDKnc0ZI8Tp45pnsM04GiZFqIXmFn4azjUNPVRLl4aynRrQsb4dVz3fkv7RpY7/wekOvSmwrvumF5TNwlnd8YDoCjyXtMdXuWRcMn3tGN8Th3JnrE17gblV2vhK0avaPKV5m+VztXE9JKQI1mjwxLdmGXE33RNtbuE8RqCS/qy8qx94ljnVY0tG4/cmxGnBGtyjbwpfDk061xKr8WBgMS2xp9sakWOwueaNaXHmCzOaW5rqOSE1iWxi1Vl4FznUNb0lWMPAN3xpB1Bas76jH5jZjZVntEx9nYrKzMVna+CkselHDm17FHZZnN1BHSFHbwmsxeR2U4fEsEmysVtZGqBZWK1srFrVJGzTJ9lCtbKFX2VqtbM1aVRm/SJ9nCsbOFAswVjZ
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/Lu56xVlZ40M\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d580>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('Lu56xVlZ40M', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/SWoravHhsUU\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d700>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('SWoravHhsUU', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/O8l4Kn-j-5M\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83dd60>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('O8l4Kn-j-5M', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAUDBA8QDxAQEA8QEA4QEBANEA8QEA0ODw0NDw0NDQ0PDQ0NDRANDw4PDQ0NDRUNDxERExMTDw0WGBYSGBASExIBBQUFCAcIDwkJDxUPDw8VFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFRUVFf/AABEIAWgB4AMBIgACEQEDEQH/xAAcAAABBQEBAQAAAAAAAAAAAAAAAQMEBQYCBwj/xABXEAABAwIEAgYFCAYGBgcHBQABAgMRAAQFEiExQVEGEyJhcfAHMoGRoRQjQlKxwdHSCBZi0+HxFSQzQ5LUU2Nyc5OzFyVUgqKjtBgmNESDlMQ1dLLCw//EABkBAQEBAQEBAAAAAAAAAAAAAAABAgMEBf/EACsRAQEAAgICAgEEAQQDAQAAAAABAhEDIRIxE1FBBBQiYXGBkdHwMqHhsf/aAAwDAQACEQMRAD8A+MqKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKKKKAooooCiiigKK1I6DO/Xa96/3dKz0FeP02ve5+7rHyY/bXjWVorWHoE99dr3r/d0y30LdP02vev8Ad0meN/KWaZmitMehbsxnb96/3dKvoU6Ppt+9f7ur54/aaZiitKvoa6Ppt+9f7ul/Up367fvX+7p5wZmir9XRRz6zfvX+SnHeh7o+k371/eiruJuM5RWsw3oC+tQTmbTOsqLgEc9Gz8KuH/RFcjXrGCOYU6AO45mRrUueM91XndFb1r0VXJmFs6ftOfuq7X6J7kGOsY3j1ndfD5ms/Lh9jz+it8fRRcwDnZAM/Sc4b/3VIPRXcf6Rj/E5+6p82H2bYKivRcF9Dt28YQpnQwSVOAJ7yeq2r0hj9DvFCARcWEHX+1uv8nW8cpl6NvnKivpD/wBjbFf+0WH/ABbr/J0f+xtiv/aLD/i3X+TrWh830V9If+xtiv8A2iw/4t1/k6RX6HGK/wDaLD/i3X+TpqpuPnCivoO8/RJxJAlVxYAd7twPttBVXjP6MWJNICyu2Uk69hVwpX+D5MFa9wNNG48QorZ/9Gl1wTm49lD6tBuYDMwOcVBPQm4mMupMAZXZJ7h1c1nca0zVFaXEOhL7ailQAI0I7f5Kl2vo5uVAEZIPMq25+pU88fs0x9FalzoI+DEomJ3V+Sop6KO80nUDTPuf+5TyiKCirp7o4tJIKkAjgc4PL6lWeFdAnXEZw6ylMkdpTgOncGjTzgyVFbBPo+eOzjJ4bufe1TzXo1fP94wPFTv3M1Pkx+03GJor0geh64ievtf8b3+XqLinomvEbdW4ImWytQHHWW0ke6r5w8owNFabDehD7isqAlSuQzaePZrSI9DF3AJWwJ4Fbk/Bkj408objzWivRFeiK5mOsYka+s7t/wAGmnfRTcjdxj/E5+5qfJj9p5RgKK1j/QJ4fTaPgpf3timT0Ke+s371/kqfLh9ruMzRWn/Ul76zfvX+Sl/Uh76zfvX+SnzYfZuMvRWqPQR76zfvX+Sj9RXvrN+9f7up82H2eUZWitV+or31m/ev93R+or31m/ev8lPmw+zyjK0Vqv1Fe+s371/u6P1Fe+s371/kp82H2eUZWitV+or31m/ev8lH6ivfWb96/wB3T5sPs8oytFak9BnvrN+9f7ugdBnvrN+9f7unzYfZuMtRWpHQZ76zfvX+Sk/Ud76zfvX+7q/Nh9nlGXorUfqO99Zv3r/JQehD31m/8SvyU+bD7PKMvRWo/Uh76zf+JX5KD0Ie+s371/kp82H2bj0lQBFSE2+XSoFthylglO06ew61obQEA6Ep7KVKjQHhrsJFeHxrvctKxxgkQNzVPb2CgCojQb16DYuoCjBAVHrq9VqeSfpKI0nTeqXpHeNklASqVKBkbEjidfaa1hlrpjKysihBOoOvtqMlSiSNZFalsQDMDX2mpNu02Spfqg8RrA0nTma6TOM1n7a0UTrpGknaY50zckxB47d9bly6bDXAIj+z3UpR/vFHQTyGtUWHpauHVFQUEhMagbjgk7VfLdZv0pm7dIE1IYSgmPdPCkxoozKQkEQYFQGsJjdWp1jetyyzdrnpqcOfQFQDMSAduFXuG2zzsI9YTJjQAftHaPGs1ZMhCdjJEydM1anAMRLSScxQkmJ4HTY8/dWL27YxL6sNKIkGNNNtOVMOuErBjsyDP21HvXAVHLrzUTz5VLtLWUg5oAEnvrzZdFic4hsgZtt/EzVNiFzmCgkQAYBprFLvRIRxMVFtVETOoMGeH8daxjj+a53axwl8oGpG8kSYUORykH419OeiL0gNXCQ0crbyRGWdFAcU/hXybdrAOaY/Cm7LGlJWkoJSdwudRFevgzuP+Cbr78pa+e/Rp6eU9lq6IJ2Dg/8A7CvXLj0gWSACu5aROvaWAfdvXvnbO2nNNvDSsvbeknD1aJu2D/8AUSPtrQWOItuCW1oWOaVBQ94NVUV+1SNfiftrA9OemIaPVxuNVE7jiBW6xtSspywTymJ568K+aPSrerU4Qc6coWRmTppuAvY6d9c+a2Y9JWgxu9LygpKgkFOVWUxoRqBHCOzWLx28BkaZ06Ax2gBwB/Co/Q6xcyJWqeqWoDrCTCRJBCeBM78hTGKW0KBBmNCR3HSTzO814OW5Sd9G6rLrCi4dAcx1mp/RfAHnZQ3qpJhYOkjcQo9kcdNJqaziq0rGUAqJCQBqduW0xXpnQbA1Bku5wjrD2xGpiRqeHurXBjbWvPTxy9wV/M63lSFZRJUNUJBmU5Qd9BmqFYdGFuIVleZKxA6spyKRAOyp1M6TGvdXqHSfA3ApbrSsygkhUK1yEkAZTx30HCvObzBlJOftJVoJI0kneRqI763yXXpdvOunVtCe0iHEKy5gZBTGo9hj41D6IYilIhR55dJEnf8AGvQMZwkLaWhSu3Bg79reZ76836MMdW+kuNhYSZKDsrzvWOPPyi2tdYvBSZQVFRlJ7BygzpBmDIq2XbOdWJSVQdNNh3kd9SrrGM6f7MJg5kxsEjSpGAYqoZiPogEyeExtS3HbFylSbaw6poOSFFXPbXgB3Uxe4ipKh29CBoNBqdRU64faKE5pAEHiQo/VGnDnVRfMpdcOXspjeIgAd1LZrpk/bKS2czSQD9KOPjXSccPxn38KpEOakDQbSOIpG0qSdQddRPHka57tSxZXOIkmRvt8aYvpVrNV9qok+2pCLiFfdWOxCLEE00/TuIXHxqEyJNY0pIrsU8WRXCm6gRJrsVzSioFFFFFQFBoooEopaKoSig0k+fPnegTz8fOlA+PkCikUB5318/ZVCefHz7qD5+6l/n546bUgHn+dUBHn7d6Qjz/LuA90UAedudCfPhPfqd9tao21mtAVATmQn6O0jvI99V9+skHLIb3IGgnv8K5ceUBIIEo1gAagbHme+n7CydchuFBa0pyjYARmlR2EDWTtXorqz79xlBk/H7eewqwsGUlCShRDhnNoMoHCDxkcKlKwtlTRDgEpUe2DB9aD4jlNR7a1yyhCoCB7xXHPOb1HSTpVYtiSELEakQdeKhyHKaq7nGFKObitWwG5J5Ac+Ap++wJanpMzEg+w/wA6vOj/AEYIWl2BlSUgToVEEFRA45R50r1Ya8ZHKy2qrRSkhakgTCpdZCk8+ypwEEfVIBFTm1ZT2Xm8gOiettwVcifnIGlYstxFa70f+ji8vkvLtWs6WBLiipKBJSpSUInVbhCD2UgxKcxTmTNy4pZpdItzaEnMVsk8IfY08fnN66TYECQ4ySeHXsSPH5yKhdBMAevX27e3AU66FFAKggEIbU4rtK0HYSTXLm
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/B1Dk_9k6l08\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83db20>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('B1Dk_9k6l08', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/4J0cpdR7qec\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d9a0>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('4J0cpdR7qec', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/Kx-2PyrhnFE\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d490>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('Kx-2PyrhnFE', width=800, height=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"800\"\n",
       "            height=\"600\"\n",
       "            src=\"https://www.youtube.com/embed/fN-bQddbbUI\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.YouTubeVideo at 0x13c6c83d760>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IPython.display.YouTubeVideo('fN-bQddbbUI', width=800, height=600)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "* https://thispersondoesnotexist.com/\n",
    "* https://thiscatdoesnotexist.com/\n",
    "* https://blog.openai.com/better-language-models/\n",
    "* https://affinelayer.com/pixsrv/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## 1.3. Metody uczenia maszynowego"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Z jakimi rodzajami zadań mamy do czynienia?\n",
    "\n",
    "* Uczenie nadzorowane\n",
    "  * Regresja\n",
    "  * Klasyfikacja\n",
    "* Uczenie nienadzorowane\n",
    "  * Klastrowanie\n",
    "* Uczenie przez wzmacnianie\n",
    "* Systemy rekomendacyjne"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Klasyfikator\n",
    "\n",
    "* Klasyfikator to funkcja $h$, która przykładowi $x$ przyporządkowuje prognozowaną wartość $h(x)$.\n",
    "* Jeżeli funkcja $h$ jest ciągła, to mówimy o zagadnieniu **regresji**.\n",
    "* Jeżeli funkcja $h$ jest dyskretna, to mówimy o zagadnieniu **klasyfikacji**."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Algorytm uczący\n",
    "\n",
    "* Dane są przykładowe obserwacje $(X, y)$.\n",
    "* Staramy się dobrać funkcję (klasyfikator) $h$ tak, żeby $h(x) \\sim y$."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "W jaki sposób można określić, czy klasyfikator jest „dobry”?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Podział metod uczenia maszynowego\n",
    "\n",
    "> \\[Każdy algorytm uczenia maszynowego\\] stanowi kombinację dokładnie trzech składników.\n",
    "> Te składniki to:\n",
    "> * reprezentacja\n",
    "> * ewaluacja\n",
    "> * optymalizacja\n",
    "\n",
    "> &mdash; Pedro Domingos, “A Few Useful Things to Know about Machine Learning”"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Reprezentacja\n",
    "\n",
    "* drzewa decyzyjne\n",
    "* regresja liniowa\n",
    "* regresja logistyczna\n",
    "* naiwny klasyfikator bayesowski\n",
    "* algorytm $k$ najbliższych sąsiadów\n",
    "* sieci neuronowe\n",
    "* maszyny wektorów nośnych\n",
    "* algorytmy genetyczne\n",
    "* ..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Ewaluacja\n",
    "\n",
    "* skuteczność (dokładność)\n",
    "* precyzja i pokrycie\n",
    "* błąd średniokwadratowy\n",
    "* _information gain_\n",
    "* _logistic loss_\n",
    "* BLEU\n",
    "* ..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Optymalizacja\n",
    "\n",
    "* optymalizacja kombinatoryczna:\n",
    "  * wyszukiwanie zachłanne,\n",
    "  * _beam search_...\n",
    "* optymalizacja ciągła:\n",
    "  * nieograniczona:\n",
    "    * metoda gradientu prostego,\n",
    "    * metoda Newtona...\n",
    "  * ograniczona:\n",
    "    * programowanie liniowe..."
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.8.3"
  },
  "livereveal": {
   "start_slideshow_at": "selected",
   "theme": "white"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}