Course Prerequisites
- ENGR 102 Engineering Lab I – Computation
- MATH 251 Engineering Mathematics III
Course Description
- Engineering application-focused introduction to Machine Learning covering key machine learning concepts, guidance on selecting machine learning models, and application of python-based tools for data preparation, model development, and performance evaluation. Practical engineering use-cases for machine learning from electronics, energy, motors, robotics, security, computer systems, and health. Machine learning laboratory projects including dataset management, ML model development, visualization, and practical application showcasing ML expertise.
Course Objectives
- Identify the basic techniques used in learning systems in real-world engineering applications. Skills gained through text, lecture, labs, and final project.
- Format, manipulate, and interact with engineering datasets in Python
- Apply dataframe management methods to overcome missing, non-numerical, and grossly incorrect values in a dataset
- Characterize data with common statistical techniques.
- Identify appropriate learning techniques for representative engineering applications.
- Apply regression techniques for engineering problems.
- Model and solve engineering classification problems with several classification techniques.
- Develop and train neural networks for image detection and signal analysis problems.
- Identify important limitations in the application of machine learning, including ethics issues, through class discussion and case-study evaluations.