Course Description

Let's start with a bit of historical perspective. For centuries, engineering problem-solving rested on two fundamental pillars: theory and experimentation. Think of Maxwell's equations guiding our understanding of electromagnetism, or Faraday building physical prototypes to test his ideas. Then, in the latter half of the twentieth century, simulation emerged as the third pillar. We could model complex systems using finite element analysis or circuit simulators before ever building a physical prototype. Today, we are witnessing the emergence of a fourth pillar: data-driven engineering, powered by machine learning. Now, I want to be very clear about something. Machine learning does not replace the first three pillars. It doesn't make Maxwell's equations obsolete, and it doesn't eliminate the need for careful experimentation or simulation. Rather, it augments them. Machine learning helps us model complex systems where first-principle models are either too slow to run in real-time or too inaccurate because the underlying physics are simply too complex to capture perfectly. It gives us a new way to extract insight from the vast amounts of data our modern engineering systems generate every second.

What you'll learn in this course?

• Distinguish between Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) within engineering systems.

• Identify key machine learning applications in electrical engineering, including Smart Grids, Motor Fault Diagnosis, and Signal Processing.

• Understand different types of engineering data such as tabular data and time-series data and their influence on algorithm selection.

• Match common machine learning techniques-Regression, Classification, and Clustering-to relevant engineering problems.

• Describe the major steps involved in a typical machine learning project workflow.

Prerequisites

• Basic engineering mathematics, statistics, and data interpretation

• Familiarity with electrical engineering systems and basic programming is helpful