{
  "fetched_at": "2026-10-20T08:44:26Z",
  "source_url": "https://www.kaggle.com/competitions/cs446-fa17b/data",
  "pages": [
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>Team mergers are not allowed in this competition.</p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>There is no maximum team size.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 2 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>TBA</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>2/1/2014 12:00 AM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": " ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "#Overview\n\nFMRI is a technology used to measure brain activity, typically while the subject is performing a task in the MRI scanner. It works by measuring how blood flow changes in response to neuronal activity. The resulting data are a time series of brain volumes. After pre-processing, we can compute fMRI brain maps which roughly reflect locations of brain activity corresponding to the task the subject was involved in i.e. a single map for each subject/activity. One important topic in neuroscience is to assess to what extent one can predict behavior from fMRI brain maps. This is known as “decoding” or “brain reading” [2, 3]. Each brain image may be associated with multiple cognitive processes (sub-tasks). Ideally, decoding can predict which sub-tasks are associated with each brain map [1] -- denoted as a set of labels. \nThe prediction problem which involves predicting a set of labels is known as multilabel classification. It is often thought of as the simplest kind of structured prediction [4, 5]. \n\nReferences:\n\n[1] Schwartz, Yannick, Bertrand Thirion, and Gaël Varoquaux. \"Mapping paradigm ontologies to and from the brain.\" Advances in neural information processing systems. 2013.\n\n[2] Varoquaux, Gael, and Bertrand Thirion. \"How machine learning is shaping cognitive neuroimaging.\" GigaScience 3.1 (2014): 28.\n\n[3] Pereira, Francisco, Tom Mitchell, and Matthew Botvinick. \"Machine learning classifiers and fMRI: a tutorial overview.\" Neuroimage 45.1 (2009): S199-S209.\n\n[4] Tsoumakas, Grigorios, and Ioannis Katakis. \"Multi-label classification: An overview.\" International Journal of Data Warehousing and Mining 3.3 (2006).\n\n[5] Koyejo, Oluwasanmi O., et al. \"Consistent multilabel classification.\" Advances in Neural Information Processing Systems. 2015.\n\nYour goal is to predict a set of labels associated with each fMRI brain image. You can use any technique you like. Your project will be judged based on performance on two metrics: *Subset Accuracy* and *Micro-averaged AUC*. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}