{
  "fetched_at": "2026-10-19T11:59:31Z",
  "source_url": "https://www.kaggle.com/competitions/digit-recog/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The data files train.csv and test.csv contain gray-scale images of hand-drawn digits, from zero through nine.\n\nEach image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 255, inclusive.\n\nThe training data set, (train.csv), has 785 columns. The first column, called \"label\", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image.\n\nEach pixel column in the training set has a name like pixelx, where x is an integer between 0 and 783, inclusive. To locate this pixel on the image, suppose that we have decomposed x as x = i * 28 + j, where i and j are integers between 0 and 27, inclusive. Then pixelx is located on row i and column j of a 28 x 28 matrix, (indexing by zero).\n\nFor example, pixel31 indicates the pixel that is in the fourth column from the left, and the second row from the top, as in the ascii-diagram below.\n\nVisually, if we omit the \"pixel\" prefix, the pixels make up the image like this:\n\n\n000 001 002 003 ... 026 027\n\n028 029 030 031 ... 054 055\n\n056 057 058 059 ... 082 083\n\n |   |   |   |  ...  |   |\n\n728 729 730 731 ... 754 755\n\n756 757 758 759 ... 782 783 \n\nThe test data set, (test.csv), is the same as the training set, except that it does not contain the \"label\" column.\n\nYour submission file should be in the following format: For each of the 25000 images in the test set, output a single line containing the ImageId and the digit you predict. For example, if you predict that the first image is of a 3, the second image is of a 7, and the third image is of a 8, then your submission file would look like:\n\n\nImageId,Label\n\n1,3\n\n2,7\n\n3,8 \n\n(27997 more lines)\n\nThe evaluation metric for this contest is the categorization accuracy, or the proportion of test images that are correctly classified. For example, a categorization accuracy of 0.97 indicates that you have correctly classified all but 3% of the images.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "### ***Start here if...***\n\nYou have some experience with R or Python and machine learning basics, but you’re new to computer vision. This competition is the perfect introduction to techniques like neural networks using a classic dataset including pre-extracted features.\n### \n**Competition Description**\n\n*MNIST* (\"Modified National Institute of Standards and Technology\") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.\n\nIn this competition, your goal is to correctly identify digits from a dataset of tens of thousands of handwritten images. We’ve curated a set of tutorial-style kernels which cover everything from regression to neural networks. We encourage you to experiment with different algorithms to learn first-hand what works well and how techniques compare.\n\n### **Practice Skills**\n\n    Computer vision fundamentals including simple neural networks\n\n    Classification methods such as SVM , K-nearest neighbors or Random forest classifiers\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## **Goal**\n\nThe goal in this competition is to take an image of a handwritten single digit, and determine what that digit is.\nFor every in the test set, you should predict the correct label.\n\n## **Metric**\n\nThis competition is evaluated on the categorization accuracy of your predictions (the percentage of images you get correct).\n\n## **Submission File Format**\n\nThe file should contain a header and have the following format:\n\nImageId, Label\n\n1,0\n\n2,0\n\n3,0\n\netc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}