MATH 466 · also MATH 766
Mathematics of Machine Learning
Paul Louis Bendich
Description from DukeHub
The course will explore mathematics underlying the practice and theory of various machine learning concepts and algorithms. Kernel methods, deep learning, reinforcement learning, generalization error, stochastic gradient descent, and dimension reduction or data embeddings will be introduced. The interplay between the mathematics and real applications will be a component of the course. Students can take both this course and Mathematics 465 for credit. Recommended prerequisite: Mathematics 230/340 and 218/216/221 and some familiarity with programing, preferably Python.
Skills
- programmingdescription: "algorithms" and 1 more
- data and statisticsdepartment: MATH
- ai and machine learningtitle: "machine learning"
AI-resilient: 0 of 5
- No: Physical, lab or field work
- No: Live work with people
- No: Judgment someone is accountable for
- No: A craft you practice with your hands or body
- No: Small, in-person format
The checks lean on Microsoft Research, Working with AI (2025), which found generative AI applies least to physical work and hands-on work with people. A signal, not a promise. How the score works
More in MATH
- Laboratory Calculus and Functions I MATH 105L
- Laboratory Calculus and Functions II MATH 106L
- Laboratory Calculus I MATH 111L
- Laboratory Calculus II MATH 112L
- Elements of Mathematical Modeling MATH 160CN
- Multivariable Calculus for Economics MATH 202D