Section 1.1

Adding in information for Section 1.1 (definition of CV, etc)

Author: Wei-Ji-Chen

2023/SP23/intro-cv-series/workshop-1/Intro_to_CV.ipynb

@@ -1,144 +1,169 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
       "cell_type": "markdown",
-      "source": [
-        "# Intro to CV Workshop 1: Getting Started with Computer Vision"
-      ],
       "metadata": {
         "id": "lrPpS1rpCK-h"
-      }
+      },
+      "source": [
+        "# Intro to CV Workshop 1: Getting Started with Computer Vision"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "## Section 1 - Overview of Computer Vision\n"
-      ],
       "metadata": {
         "id": "X_yXZfg-9Fa-"
-      }
+      },
+      "source": [
+        "## Section 1 - Overview of Computer Vision\n"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 1.1 Introduction of Computer Vision\n"
-      ],
       "metadata": {
         "id": "t-rte0n6Jrn5"
-      }
+      },
+      "source": [
+        "### 1.1 Introduction of Computer Vision\n"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {},
       "source": [
-        " ### 1.2 The MNIST Dataset"
-      ],
+        "Welcome to Intro to Computer Vision! This will be a three part workshop series focused on building an overview of the underlying algorithms and applications of Computer Vision. For today's workshop, we'll be focusing on PyTorch - a machine learning framework used for AI applications - and neural networks - the foundational concept underlying computer vision algorithms such as CNN (Convolutional Neural Networks) that power visual imagery analysis. Let's get started!"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "What is Computer Vision? \n",
+        "\n",
+        "Computer Vision is a subfield of AI that focuses on computers deriving and understanding information based on visual data - images, videos, etc"
+      ]
+    },
+    {
+      "cell_type": "markdown",
       "metadata": {
         "id": "LAy-avyOKTPw"
-      }
+      },
+      "source": [
+        " ### 1.2 The MNIST Dataset"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "## Section 2 - Basics of basics"
-      ],
       "metadata": {
         "id": "TknP7gWmCJvB"
-      }
+      },
+      "source": [
+        "## Section 2 - Basics of basics"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 2.1 Pytorch Basics"
-      ],
       "metadata": {
         "id": "xClsDXlOJNZM"
-      }
+      },
+      "source": [
+        "### 2.1 Pytorch Basics"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 2.2 Model Training and Evaluation"
-      ],
       "metadata": {
         "id": "vKDff4XKJgx_"
-      }
+      },
+      "source": [
+        "### 2.2 Model Training and Evaluation"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "## Section 3 -  Formulating a Machine Learning problem "
-      ],
       "metadata": {
         "id": "pcibKmYR_OTW"
-      }
+      },
+      "source": [
+        "## Section 3 -  Formulating a Machine Learning problem "
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "(feel free to edit the outline)"
-      ],
       "metadata": {
         "id": "tIpm_ep-K3lQ"
-      }
+      },
+      "source": [
+        "(feel free to edit the outline)"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 3.1 Set up MLP Architecture (NN layers, activation function)\n"
-      ],
       "metadata": {
         "id": "hanQrmfxCH5C"
-      }
+      },
+      "source": [
+        "### 3.1 Set up MLP Architecture (NN layers, activation function)\n"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 3.2 Loss function and  Regularization (L1/L2/Dropout)"
-      ],
       "metadata": {
         "id": "k2zSw1jLKvM9"
-      }
+      },
+      "source": [
+        "### 3.2 Loss function and  Regularization (L1/L2/Dropout)"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "### 3.3 Learning and Evaluation (Gradient Descent, SGD)\n"
-      ],
       "metadata": {
         "id": "ZAqFgipcKx6S"
-      }
+      },
+      "source": [
+        "### 3.3 Learning and Evaluation (Gradient Descent, SGD)\n"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "## Section 4 - Making a MLP piece-by-piece"
-      ],
       "metadata": {
         "id": "7gJNzxuBLDyv"
-      }
+      },
+      "source": [
+        "## Section 4 - Making a MLP piece-by-piece"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "## Section 5 - Putting it together for CV (Can change this later)"
-      ],
       "metadata": {
         "id": "tbIiaUguLUoU"
+      },
+      "source": [
+        "## Section 5 - Putting it together for CV (Can change this later)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3.10.7 64-bit",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python",
+      "version": "3.10.7"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
       }
     }
-  ]
-}
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}