{
  "fetched_at": "2026-10-19T10:08:36Z",
  "source_url": "https://www.kaggle.com/competitions/blg527e-spring-2022-term-project/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>Data Description</h2>\n\n<p>You are given three different data files which are train_LR, train_HR and test_LR. Both training files should be used to build your machine learning model. In the training sets, you are given low-resolution(LR) and high-resolution(HR) connectivity matrices of brain. First, you will use 5-fold cross-validation on the training set to design your model which predicts HR brain connectivity sample from an input LR sample. This will allow you to evaluate the generalizability and performance of the model. Once the model is fixed (no more changes in its composing components), you can retrain it using the whole train set, then test it on the independent test set to predict test_HR —which is the solution file that you are NOT given. You will submit your predictions through Kaggle, and your file will be evaluated and scored which will be shown in Leaderboard.</p>\n\n<p>Once you obtain your predicted test_HR, melt it (see project PDF file) and upload it to the system.</p>\n\n<h2> File Descriptions</h2>\n<ul>\n<li>train_LR.csv: the training set for low-resolution matrices</li>\n<li>train_HR.csv: the training set for high-resolution matrices</li>\n<li>test_LR.csv: the test set for low-resolution matrices</li>\n<li>sampleSubmission.csv: A sample submission file</li>\n</ul>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this challenge, we ask you to apply the tools of machine learning to predict the high-resolution brain connectivity matrix from low-resolution connectivity matrix of the same brain.\n\nRead the project PDF for further instructions. Check the \"Data\" tab above to access the data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2> Scoring Metric </h2>\n<p> You are going to use Mean Squared Error as scoring metric</p>\nYou will get 20 points in total from your Kaggle rank. Your points will be calculated as follows:\n\n&gt; 5 + 15*(1-normalized\\_MSE\\_result)\n\nand the normalized MSE results will be calculated by applying min-max normalization rule:\n\n&gt; normalized\\_mse = [your\\_mse - min(all teams)] / [max(all teams) - min(all teams)]\n\nA demonstration:\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F5065607%2F390866c61115365457db79244e10fb56%2Franking.png?generation=1589825921021556&amp;alt=media)\n\n\n<h2> Submission File Format</h2>\nThe file should have exactly 2 columns:\n- ID (integer)\n- Predicted value\nYou can download the sample submission file (sampleSubmission.csv) on the Data page.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}