This course introduces core machine learning algorithms with a focus on applications in solid mechanics.
Students will learn to implement and apply models using Python to analyze engineering data such as stress-strain behavior, material classification, and surrogate modeling of FEM outputs.
While key mathematical concepts like linear algebra and optimization are covered, the emphasis is on practical understanding and hands-on coding.
Topics include: Python programming, linear algebra, optimization, regression, classification, clustering, statistics, PCA/SVD, neural networks, Bayesian optimization, etc.

* Basic experience with Python programming
* Familiarity with linear algebra and introductory calculus
* Prior coursework in mechanics of materials or solid mechanics is recommended

TBD

Week 1: Introduction & Python Review
Week 2: Linear Algebra Refresher
Week 3: Optimization I
Week 4: Optimization II
Week 5: Regression Models
Week 6: Classification Techniques
Week 7: Model Evaluation
Week 8: Midterm Exam
Week 9: Engineering Statistics
Week 10: Dimension Reduction (PCA, SVD)
Week 11: Neural Networks I with PyTorch
Week 12: Neural Networks II – Surrogate Modeling
Week 13: Bayesian Concepts
Week 14: Bayesian Optimization
Week 15: Final Project Presentations
Week 16: Final Exam

Lecture-based