{
  "fetched_at": "2026-10-19T07:56:34Z",
  "source_url": "https://www.kaggle.com/competitions/cisc873-dm-f21-a3/data",
  "pages": [
    {
      "name": "data-description",
      "content": "✔️ The related datasets for this assignment. You can download the datasets and directly upload them to Google Collab through the web interface.\n\nAlternatively, you can directly execute:\n! wget https://github.com/CISC-873/Information-2021/releases/download/data/a3.zip",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "### Chest X-Ray Classification Problem\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4409738%2F68508ec0f0cba8900383ba6681b80249%2F2f9.jpg?generation=1603430395814767&alt=media)\n\n\nIn this assignment, we are going to predict if the chest x-ray image is covid-19 positive or negative.  The images are collected from different sources, were taken in different machines, and come with different resolutions. This assignment focus on an end-to-end learning framework, so we don't assume any bio-medical background, and it is not recommended to do any feature extractions on the images. Instead, we will use a neural network trying to identified the images are infection positive. \n\nDue to the limited timeline, you will be starting from our existing code template. The template just serves as a starting point for you, and you will still need to swap things and observe the performance. The dataset is small and the result is less predictable. So we reduced the weight for ranking score.\n\n\nEnjoy! \n\n\n### Tasks:\n\n✔️ Meme competition:\nInclude/find a MEME that you liked related to data science/data mining/machine learning\n\n✔️ Understand the template:\nPut detailed comment on each line of the code to show your understanding of the template (you can find it at the Data tab). Then describe: What is the experimental protocol used and how was it carried out? How did we tune hyper-parameters in the template? What is the search space and what is the criteria to determine good/bad hyper-parameters? \n\n✔️ Problem Formulation:\nDefine the problem. What is the input? What is the output? What data mining function is required? What could be the challenges?  What is the impact? What is an ideal solution?\n\n✔️ Model Tuning and Documentation:\nNow based on the template, try to improve the model's performance on the public leaderboard by following the data science life-cycle for tuning. You can try different features, different hyperparameters/configurations of the model, and even a different model. For each trial, document the reason why you want to make the certain change and the expected outcome, before running the code. Record the observed performance and your thought on it. Recall that we have a DS life-cycle and we should know what to do when underfit/overfit. The final result is not important, but the process is. Documentation of your thought process is very important, since most people forgot why they test certain model/hyperparameter after they got the result (it takes time). It also helps a lot when you got stuck. You can organize the notebook by listing \n\n- thoughts and observations for trial 0, plan for trial 1\n- code for trial 1\n- thoughts and observations for trial 1, plan for trial 2\n- code for trial 2\n...\n\nYou have to tune at least 10 times. All the tried solutions should be different (e.g. different feature sets/different preprocessing). The tried solutions should cover at least:\n- Try to fine-tune the design of a fully-connected neural network model (number layers, learning rate, epochs etc.)\n- Try to add data augmentation to your fully-connected model. Instruction/example is [here](https://www.tensorflow.org/tutorials/images/data_augmentation#use_keras_preprocessing_layers).\n- Swap the template with convolution neural network with pooling layer. Try out tuning different settings (filters, layers, kernels etc)\n- Bonus: transfer learning and up-training on existing models. Instruction/example is [here](https://www.tensorflow.org/tutorials/images/transfer_learning).\n\n\n✔️ Answer the questions below (**briefly**):\n\n🌈 What is the validation method used in the example template? Considering the dataset is a bit small, is it an appropriate approach? If not, what would you suggest? (you are not expected to change but you are allowed to do that if you want)\n🌈What is the default model in the template? Is it a good one for image data? why?\n🌈Convolution neural network address what issues of a fully connected neural network and how?\n🌈What's the different between 1d, 2d, and 3d convolution? \n🌈What is the difference between convolution and pooling?\n\n### Deliverable:\n\n🔥 A python notebook containing the documentation of how you reach the final design as well as the answers to the questions. \n\n\n### Marking:\n\n👍 1 for technical soundness of the final script (whether you did things right e.g. not using ID as a feature, tuning ranges reasonable e.g. not a giant search space for grid search)\n👍 2 for clarity, organization and soundness of the documentation (how & why you adjust your design to improve the performance) (example deduction: decision tree with observed high bias -> trim more, linear model with observed high bias in testing set -> more regularizations)\n👍 1 for the clarity of your own code (all the template code and **new** code should have comments)\n👍 4 for meeting the requirements (what to cover) for all the trials.\n👍 2 your answers to the questions (deductions based on errors)\n\n1 bonus point if you do transfer learning and up-training  \nNote: Emoji allowed and encouraged so it will be more fun for us to grade it.\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "In this assignment, we will use AUROC as a metric on the predicted probability:\n\nhttps://en.wikipedia.org/wiki/Receiver_operating_characteristic",
      "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\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}