القروب رقمه ٥ في الملف المرسل

المتطلبات Link (1): https://keras.io/api/applications/ Link (2): https://www.tensorflow.org/datasets/catalog/ Link (3): https://huggingface.co/datasets Link (4): https://www.kaggle.com/datasets [Each group can have a maximum of 4 – 6 students] [The deadline is on Saturday, 13/12/2025, at 11:59 PM] The group presentations are scheduled to take place during the last Week of 18th [14/12/2025 (Sunday) - 18/05/2025 (Thursday) ]. [3 Marks] Step (1). Frame the Problem: Use previous links to complete step (1) of your project, which is framing the machine learning problem. You should answer the following questions to complete this Step: (Please refer to Lab 03 (Understanding the Universal Workflow of Machine Learning) for more information about how to frame an ML problem) What will your input data be? What are you trying to predict? What type of machine learning task are you facing? Binary classification Multiclass classification Scalar regression Vector regression Multiclass, multilabel classification Image segmentation Ranking clustering generation or reinforcement learning [4 Marks] Step (2). Build the Model: Use previous links to complete the second step of your project, which is building and evaluating your machine learning model. [3 Marks] Step (3). Prepare your project presentation and report. Your report must include the following: 1. Project Title (Slide 1) 2. Project Team Members (Slide 1) 3. Project Overview (Slide 2) 4. Project Goals and Objectives (Slide 3) 5. A summary of step (1) outcomes, such as: (Slides 4 and 5) What will your input data be? What are you trying to predict? What type of machine learning task are you facing? binary classification Multiclass classification Scalar regression Vector regression Multiclass, multilabel classification Image segmentation Ranking clustering generation or reinforcement learning 6. A summary of your dataset (Slide 6) 7. A summary of your model and data preprocessing techniques (Slides 7 and 8) 8. Information about evaluation matrices, loss function, optimizer, and training process of your model (Slides 9, 10, and 11) 9. A summary of your model evaluation results (including graphs showing accuracy and loss of training and validation datasets, testing set loss, accuracy, and confusion matrics if applicable) (slides 12, 13, and 14) 10. Conclusions, an overview of what you have done and learned during this project (Slides 15) Submissions: - Submit your report as a PowerPoint file. - Submit a link to your project folder on Google Drive. - One submission per group is enough.

large