AI 351: A Mathematical Approach to Machine Learning

Title: A Mathematical Approach to Machine Learning with Pytorch
Instructor:  Tony Shaska
Offered: Winter 2024 (Oakland Univ.)
Meeting Times: MWF 9:20-10:27
Prerequisites Linear Algebra, Calculus III

Most machine learning workflows involve working with data, creating models, using hyperparameters to optimize model, saving and inferencing the trained models. This class introduces you to mathematical foundations of machine learning and a complete machine learning (ML) workflow implemented in PyTorch, a popular ML framework for Python.

Resources

Part I: Fundamentals

Textbook:  Mathematics for Machine Learning, Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong

Chap 2: Linear Algebra
Chap 3: Analytic Geometry
Chap 4: Matrix Decomposition
Chap 5: Vector Calculus

Chap 9: Linear Regression
Chap 12: Classification with Support Vector machines

Part II: Special Topics

Projects


Literature

Links of interests