Embedded Files
We have explored how machine learning models are built and applied in controlled settings. This module shifts the focus toward evaluating, adapting, and deploying ML models in real-world applications. We will learn how to measure a model’s performance using metrics such as accuracy, precision, and recall, as well as why these metrics matter when working with real data. We will also introduce transfer learning, showing how pre-trained models can be adapted for different tasks. Finally, we will bring together all program concepts by deploying a machine learning model onto a robotic platform, RockBot. This case study will walk you through the process of data collection and experimentation, project planning, and code selection.
This is important to understand a model's effectiveness in finding the accurate predictions, especially when given new and real data. This activity discusses to analyze a Machine Learning Model's performance as it develops its accuracy, precision, and recall.
Transfer learning is when a model is pre-built on the framework of another Machine Learning Model that was trained for effectiveness in a different task. This activity walks users through transferring and using a pre-built YOLOv8 model for object detection.
Machine learning is only a tool used in larger projects and other real-world applications. This case study discusses the RockBot robot - a robotic system using machine learning for future autonomous navigation purposes. Learn to plan a project, select and write code that aligns with project goals, and analyze the physical constraints of running a machine learning model on a robotic platform.
Page updated
Report abuse