Special Topics in Mechanical Engineering (395-0-2)

Topic

Machine Learning in Experimental Mechanics

Instructors

Horacio Dante Espinosa
847/467-5989
Technological Institute, Rm A212, 2145 Sheridan Rd, EV CAMPUS

Meeting Info

Technological Institute F280: Mon, Wed 1:00PM - 2:20PM

Overview of class

Machine Learning in Experimental Mechanics
This course provides an in-depth introduction to the application of machine learning (ML) methods in experimental solid mechanics, bridging the gap between traditional mechanics and modern data-driven approaches. Through a combination of lectures, discussions, and hands-on programming assignments, students will explore core ML techniques—including neural networks (NN), advanced neural network architectures, neural operators, and Bayesian inference—and their role in analyzing and interpreting experimental data. Each week, we will examine real-world applications of deep learning in experimental mechanics, investigating how ML models can extract insights, enhance data processing, and improve predictive capabilities. Students will develop practical skills in Python, implementing ML algorithms and leveraging datasets from GitHub to replicate and analyze results from contemporary research literature. By the end of the course, students will have built a solid foundation in ML techniques relevant to experimental solid mechanics, enabling them to apply these powerful tools to their own research and engineering challenges.

Registration Requirements

Prerequisites Linear algebra, calculus of multivariable, and basic concepts on experimentation