{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "%%html\n",
    "<!-- The customized css for the slides -->\n",
    "<link rel=\"stylesheet\" type=\"text/css\" href=\"../styles/python-programming-introduction.css\"/>\n",
    "<link rel=\"stylesheet\" type=\"text/css\" href=\"../styles/basic.css\"/>\n",
    "<link rel=\"stylesheet\" type=\"text/css\" href=\"../../assets/styles/basic.css\" />"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "remove-cell"
    ]
   },
   "source": [
    "---\n",
    "license:\n",
    "    code: MIT\n",
    "    content: CC-BY-4.0\n",
    "github: https://github.com/ocademy-ai/machine-learning\n",
    "venue: By Ocademy\n",
    "open_access: true\n",
    "bibliography:\n",
    "  - https://raw.githubusercontent.com/ocademy-ai/machine-learning/main/open-machine-learning-jupyter-book/references.bib\n",
    "---"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0MRC0e0KhQ0S",
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Convolutional Neural Network"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## The Brain\n",
    "\n",
    "- When we see something, we label every object based on what we have learned in the past\n",
    "- While vision starts in the eyes, the actual interpretation of what we see happens in the brain, in the primary visual cortex\n",
    "- The deeply complex hierarchical structure of neurons and connections in the brain play a major role in this process of remembering and labelling objects\n",
    "\n",
    "![](../images/cnn/brain.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## From Brain to Convolutional Neural Networks\n",
    "- Convolutional Neural Networks are inspired by the brain\n",
    "- The simple cells activate, for example, when they identify basic shapes as lines in a fixed area and a specific angle. The complex cells have larger receptive fields and their output is not sensitive to the specific position in the field\n",
    "- The concept of hierarchy plays a significant role in the brain\n",
    "-  In 1998, Convolutional Neural Networks were introduced in a paper by Bengio, Le Cun, Bottou and Haffner"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## How a computer sees an image\n",
    "\n",
    "![](../images/cnn/cat.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Kernel (image processing)\n",
    "\n",
    "- [Wikipedia](https://en.wikipedia.org/wiki/Kernel_(image_processing))\n",
    "\n",
    "![](../images/cnn/kernel.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## CNN architecture (1/3)\n",
    "\n",
    "![](../images/cnn/cnn-a1.png)\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## CNN architecture (2/3)\n",
    "\n",
    "![](../images/cnn/cnn-a2.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## CNN architecture (3/3)\n",
    "\n",
    "![](../images/cnn/cnn-a3.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Time to play!\n",
    "\n",
    "- https://poloclub.github.io/cnn-explainer/\n",
    "- https://adamharley.com/nn_vis/"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Feature extraction \n",
    "\n",
    "- https://ocademy-ai.github.io/machine-learning/deep-learning/CNN.html\n",
    "\n",
    "![](../images/cnn/cnn-k1.gif)\n",
    "\n",
    "[source](https://medium.com/@muhammadshoaibali/flattening-cnn-layers-for-neural-network-694a232eda6a)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Padding\n",
    "\n",
    "![](../images/cnn/padding.gif)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Pooling\n",
    "\n",
    "![](../images/cnn/pooling.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Flattening\n",
    "\n",
    "![](../images/cnn/cnn-flattening-1.webp)\n",
    "\n",
    "[source](https://medium.com/@muhammadshoaibali/flattening-cnn-layers-for-neural-network-694a232eda6a)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Full Connection\n",
    "\n",
    "![](../images/cnn/cnn-fc-1.gif)\n",
    "\n",
    "[source](https://www.linkedin.com/pulse/intro-convolutional-neural-networks-cnn-lamiae-hana/)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Acknowledgement\n",
    "\n",
    "https://www.freecodecamp.org/news/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050/"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "colab": {
   "authorship_tag": "ABX9TyOsvB/iqEjYj3VN6C/JbvkE",
   "collapsed_sections": [],
   "machine_shape": "hm",
   "name": "logistic_regression.ipynb",
   "provenance": [],
   "toc_visible": true
  },
  "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}