{
  "fetched_at": "2026-10-19T23:53:49Z",
  "source_url": "https://www.kaggle.com/competitions/2025-fitting-a-1-d-1-d-function-with-deep-learning/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Try to fit the R -> R one dimensional function with a neural network.\nYou are free to choose the architecture and training method you want.\n\nThe samples you have access to have been noised by adding a random variable with normal distribution N(0; O,1).\nThe test is done on the non-noised version of the function.\n\n\n## Files\n\n*   **1D_1D.csv** - the training set\n*   **1D_1D-test_set.csv** - the test set\n*   **1D_1D-submission_example.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "f maps elements from the set of real numbers to the set of real numbers.\nTraining examples are on [-10,10], as well as the testing.\nThe test is a mean square error (L2 norm).\n\nMarking scheme:\nWe consider that you have solved the problem if your loss score on the private set is less than `0.01`.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Your anonymized information may be utilized for conducting basic statistical analysis and for the purpose of training an ensemble learning during a TD. It is also possible that the information may be included in a scholarly publication.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}