{
  "fetched_at": "2026-10-20T05:53:39Z",
  "source_url": "https://www.kaggle.com/competitions/function-approximation-using-multilayer-perceptron/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Two datasets are given:\n* **train.csv**: the training dataset which contains three columns of data. Column 1 and Column 2 are inputs x1 and x2, while Column 3 is the target value y.\n* **test.csv**: the testing dataset for evaluating your model. Only two columns of data, i.e., x1 and x2, are given.\n\nYou need to produce the estimated value for every sample in the testing dataset using your network and save all estimated values into a file (**submission.csv**). Do not change the order of samples in the testing dataset; otherwise, your submission may get a low score due to the mismatch between your answers and the true answers.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The dataset contains the data which are the outputs from an unknown function \n$$ y=f(x\\_1,x\\_2). $$\nNote that the given training dataset has been disturbed by some noise. You are now required to design a network to remove the introduced noise. After finishing your network training, you need to produce the outputs for a given testing dataset. Kaggle will compute the **mean square error** (MSE) between your outputs and the true outputs for the performance evaluation of your network.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The criterion used to evaluate your submission is the MSE loss. \n$$L=\\frac{1}{n}\\sum_{i=1}^n(\\hat{y}_i-y)^2$$\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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 - Do not be late for submission.\n - Indicate your student ID in your username.\n - Don't cheat!\n - Apply yourself!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "File Submission Requirements",
      "content": "0. **Follow every rule below without any violation. Otherwise, your work will not be scored.**\n1. Write the code with clear comments/documentations.\n2. Write a report on HackMD platform and make it SHARED so that the teacher has the permission to read your report. Store the shared link in a text file \"REPORT_LINK.txt\".\n3. The report had better enclose the following:\n    * Detailed descriptions about the model you have design\n    * The novelty of your design\n    * What impressive results you have achieved\n    * The difficulty you encountered during the work\n    * What have you learned from the work\n2. Pack all source code files and the \"REPORT_LINK.txt\" (not including the data files) into one zip file (use winzip, not winrar) named with **\"XXXXXX_HW1.zip\" where XXXXXX is your username on Kaggle**.  (** ###### VERY IMPORTANT! ###### **)\n3. Submit the files to 東華e學苑.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}