{
  "fetched_at": "2026-10-19T12:17:39Z",
  "source_url": "https://www.kaggle.com/competitions/classifying-the-brain-on-music/data",
  "pages": [
    {
      "name": "data-description",
      "content": "For more details regarding the tasks, including the dataset download, please refer to the information provided in [this Google Colab link](https://colab.research.google.com/drive/1tbP5miE-5DXXZ5507Rh9eMlLDCWi5L2y?usp=sharing).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The training data (train.csv) consist of 160 event-related brain images (trials), corresponding to twenty 6-second music clips, four clips in each of the five genres, repeated in-order eight times (runs). The labels (labels.csv) correspond to the correct musical genres, listed above, for each of the 160 trials.\n\nThere are 22036 features in each brain image, corresponding to blood-oxygenation levels at each 2mm-cubed 3D location within a section of the auditory cortex. In human brain imaging, there are often many more features (brain sites) than samples (trials), thus making the task a relatively challenging multiway classification problem.\n\nThe testing data (test.csv) consists of 40 event-related brain images corresponding to novel 6-second music clips in the five genres. The test data is in randomized order with no labels. You must predict, using only the given brain images, the correct genre labels (0-4) for the 40 test trials.\n\nFor more details regarding the tasks, including the dataset download, please refer to the information provided in [this Google Colab link.](https://colab.research.google.com/drive/1tbP5miE-5DXXZ5507Rh9eMlLDCWi5L2y?usp=sharing)\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is **Accuracy**. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "**Programming Language:** All code must be implemented in Python. While you are permitted to use the Scikit Learn toolkit, the use of other toolkits or pretrained models, such as NLTK or transformer network architectures, for your project results is not allowed.\n\n**Project Customization:** We do not accept customized projects. You are expected to adhere to the guidelines and structure provided for the project.\n\n**Model Usage:** You are only allowed to use machine learning models discussed or that will be covered in our course. \n\n**References and Academic Integrity:** Note that you should cite all the references you refer to under each question. Proper referencing is essential for academic integrity, giving credit to original authors, avoiding plagiarism, and providing a traceable path for verification. Please check the course syllabus for more details about academic integrity.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Your objective is to classify fMRI brain images taken while listening to music in five different genres: label 0=Ambient Music, 1=Country Music, 2=Heavy Metal, 3=Rock 'n Roll, 4=Classical Symphonic. The data consists of train.csv,  labels.csv, and test.csv, for a one-person subset of a larger 20-subject study.\n\nPlease note that **the deadline for project submission is Tuesday, March 5, 11:59 pm**. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}