Skip top navigation

MATH 663: Mathematics of Machine Learning and Industrial Applications II

Important: For the most up-to-date information, refer to the official George Mason Course Catalog

General Information

Credits: 2


Basic mathematical and probabilistic models and derivations for convolutions, stability, regularization, inverse and optimal control problems, and dynamical systems in the context of semi-supervised learning. Mathematical and numerical aspects of stochastic descent methods, Nesterov accelerated gradient, AdaGrad, Adam, with applications to convolutional, deep, and ODE networks. Further applications include imaging and computer vision, saliency maps, segmentation, satellite Imagery, and physics informed learning. Offered by Mathematics. Limited to three attempts.
Registration Restrictions:

Required Prerequisites: (MATH 662*B- or 662*XS).
* May be taken concurrently.
B- Requires minimum grade of B-.
XS Requires minimum grade of XS.

Enrollment limited to students with a class of Advanced to Candidacy, Graduate, Junior Plus, Non-Degree or Senior Plus.

Students in a Non-Degree Undergraduate degree may not enroll.

Schedule Type: Lecture
This course is graded on the Graduate Regular scale.