“Simply put, machine learning is the part of artificial intelligence that actually works.” Machine learning deals with studying and building systems that can learn from data or past experiences to solve problems. It consists of a set of methods that can automatically detect patterns in data, and then use these detected patterns to predict future data, or to perform decision making under uncertainty.
Its applications include robots learning to better navigate based on experience gained by roaming their environments; medical systems that learn to predict therapies that work best for specific diseases based on existing health records; natural language processing systems that learn your speaking patterns while listening to you; and a variety of applications in which systems learn how to represent and recognize objects. It is also heavily applied in sketch recognition systems for engineering communication, outlier detection in measurements, pattern detection in engineering data, damage detection and classification, predictive modeling, recommender systems, and so on.
This NEW course offers a broad introduction to machine learning aimed at graduate ME students and upper level ME undergraduate students with strong analytical skills. We will review the main concepts behind several machine learning algorithms without going deep into the mathematics. We will explore the rapidly growing field of engineering applications of these machine learning algorithms, while gaining practical experience with them.
This graduate course deals with the mathematical modeling, computer representations and algorithms for manipulating one, two and three-dimensional solid objects on a computer; It focuses on the basic concepts of solid and geometric modeling from geometry and topology, and uses these concepts to develop computational techniques for creating, editing, rendering, analyzing and computing with models of physical objects, mechanical parts, assembly and processes.