Understand the application of machine learning in intelligent transportation and vehicles.Develop practical skills in creating and training neural networks using TensorFlow and Keras.Apply machine learning techniques, such as reinforcement learning and image classification, to transportation-related problems.Learn to implement a neural network from scratch and explore its use cases in transportation.Prepare and present a machine learning project using frameworks and tools relevant to transportation systems.

Theoretical lectures complemented with hands-on projects and assignments.Use of tools such as TensorFlow, Keras, and Python for practical demonstrations and projects.Integration of online resources like Google Colab for executing machine learning code without hardware limitations.Assignments involving the selection of scientific papers and project presentations uploaded to Moodle.

Introduction to machine learning in transportation and its applications (e.g., traffic management, truck platooning, autonomous vehicles).Overview of deep learning frameworks like TensorFlow and Keras.Step-by-step setup and implementation of machine learning models, including neural networks.Practical examples of machine learning applied to transportation, such as object detection and reinforcement learning.Project development focusing on transportation-related machine learning problems.

Practical project presentation and implementation (60% of the grade): Each student selects a machine learning task related to transportation, implements it, and presents their results in a structured format.Homework assignments (40% of the grade): Four assignments covering theoretical and practical aspects of machine learning in transportation.

Application of machine learning techniques, such as reinforcement learning, image classification, and neural networks, to transportation problems.Demonstration of understanding by creating and presenting a project, which includes:Problem definition and system architecture.Explanation of hyperparameters, optimization techniques, and model performance.Visual outputs like graphs of training performance and videos of model application.Submission of structured homework assignments focusing on theoretical and practical machine learning concepts.

Project (60%):Clear explanation of the problem and proposed solution (20%).Well-structured presentation, including system architecture and hyperparameters (10%).Performance evaluation with visual aids (20%).Quality of outputs, such as videos or graphs showcasing the model's performance (10%).Additional credit for live demonstrations and suggestions for improvement (up to 10% extra).Homework (40%):Completion and correctness of assignments.Application of machine learning principles.Code implementation and clarity of results.