{
  "fetched_at": "2026-10-19T16:11:54Z",
  "source_url": "https://www.kaggle.com/competitions/aml-2024-project1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset is based of the ``Traffic Sign Dataset'' with 54 different classes. For this work we will work with the dataset at the 75*75 pixel resolution and a subset of 9 classes that are the following: \n\n- 6 - Speed limit (70km/h)\n- 12 - Don't go left or right\n- 13 - Don't go right\n- 24 - Go right\n- 37 - Children crossing\n- 38 - Dangerous curve to the right\n- 39 - Dangerous curve to the left\n- 44 - Go left or straight\n- 50 - Fences\n\nThe dataset set is composed of 518 images, with different distribution of examples per class. \n\n## Folders\n\n*   **TRAIN** - The training set\n*   **TEST** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n*   **labels.csv** - supplemental information about the data",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Image classification is a computer vision problem where Machine Learning has obtained impressive results. In the past to tackle this task practitioners had to use expert knowledge and perform feature engineering, carefully crafting and creating visual features for Machine Learning models to learn. After this step, classical and shallow models were usually employed such as Adaboost, RandomForests, Support Vector Machines, and Multi-layer Perceptrons. \n\nDespite making their first appearance in the late 80s early 90s, Convolution Neural Networks (CNNs) became popular since 2010 due to technological advances, namely in GPU computing, and have been heavily used for image classification problems with great success surpassing most classical approaches. The main feature that this type of Artificial Neural Network provides is that feature extraction and learning is an integral part of the neural network, performing automatic feature extraction using the whole image as input, where the features are then passed to dense layers, providing the classification power as typical fully connected Multi-Layer Perceptrons are able to. \n\nIn this work, we are going to tackle an image classification dataset of traffic sign images using Artificial Neural Networks (ANNs).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Objective",
      "content": "The main objective is to analyse the dataset and create a machine learning approach with neural networks as the models that can perform supervised image classification of the dataset that is addressed in Section Dataset. To do that you should attend to the following objectives:\n\nPrepare the machine learning pipeline for the image classification dataset.\nExplore solutions and compare the results using at least, the following ANNs models:\n- Multi-Layer Perceptrons (MLP)\n- Convolutional Neural Networks (CNNs)\n\nAnd for each model, experimentation with different layer architectures, loss functions, optimisers and hyperparameters. Explore at least:\n- Loss function: MSE, Cross Entropy\n- Optimizers: RMSprop, Adam\n\nExploring other solutions than the listed ones that are suitable for the problem at hand and considered as extra work, can be as compensation points to cover problems in the listed ones above.\n\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n    ID,TARGET\n    2,0\n    5,0\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "To evaluate the generalisation ability of the developed models, we are going to use a Kaggle competition. Note that it will not impact the final mark but rather will act as a way for you to access the progress you are making and evaluate the generalisation performance of your models.\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "We present here the first practical project, part of the students’ evaluation process of the Advanced Machine Learning course of the Master in Engineering and Data Science of the University of Coimbra. This work is to be done autonomously by a group of \\textbf{two students}. The deadline for delivering the work is **7 Abril of 2024** via Inforestudante.\nThe quality of your work will be judged as a function of the value of the technical work, the written description, and the public defence. All sources used to perform the work (including the code) must be clearly identified. The document may be written in Portuguese or in English, using a word processor of your choice (Latex is preferred). **The written report is limited to 8 pages long**.\nThe document should be well structured, including a general introduction,  a description of the problem, the approach, the experimental setup, an analysis of the results, and a conclusion. The report should follow the Springer LNCS format. The Latex and Word templates are available in the Support Material of the course. The final mark will be given to each member of the group individually.\nTo do the work the student may consult any source he/she wants. Nevertheless, plagiarism will not be allowed and, if detected, it will imply failing the course. While doing the work and when submitting it, you should pay particular attention to the following aspects (whose relative importance depends on the type of work done):\n\n- description of the approach to the problem\n- description of the general architecture of the methods used;\n- description of the experiment, including a table with the parameters used which should allow full replication;\n- description of the evaluation metrics used for the validation: quality of the final result, efficacy, efficiency, diversity, or any other most appropriate;\n   \n\nDo not forget, besides what was just said, that it is fundamental: (1) to do a correct experimental analysis; (2) to do an informed discussion about the results obtained; (3) to put in evidence the advantages of the chosen alternative.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}