MATH 225Mathematical Foundations for Machine Learning
This course introduces students to essential mathematical foundations required for further studies in machine learning. The course introduces students to linear algebra (inner product vector spaces, matrix-vector products, norms for vectors and matrices, and matrix factorization), multivariate calculus (partial derivatives, gradient, Hessians, contour plots, Taylor expansion, and linear approximations), and basic optimization techniques (bisection, Newton's method, gradient descent, and the analysis of the convergence rates). Students' learning of these mathematical concepts, techniques, and methods will be facilitated by exemplary programming demonstrations and coding exercises so that the students can translate theoretical mathematical concepts into practical machine learning applications and understand the linkage between the mathematical concepts and the machine learning applications that utilize them.
Prerequisites
From the catalog: “MATH 140 and ( CMPSC 131 or ( CMPSC 121 and DS 120 )) Enforced Concurrent at Enrollment: CMPSC 132”
Where it sits in degree plans
Suggested plans most often put it in Year 2 · Fall (2 programs).
Required in (3)
- Artificial Intelligence Engineering, B.S.
- Artificial Intelligence Methods and Applications, B.S. (Capital)
- Artificial Intelligence Methods and Applications, B.S. (Information Sciences and Technology)