Learning Meets Systems and Controls

Course Description

Prerequisite: MECE 3338 or equivalent. Students are expected to be mathematically mature with a solid background in linear algebra, calculus and probability, and be familiar with basic concepts in control. Over the next decade, the biggest generator of data is expected to be devices which sense and control the physical world. This will require a rigorous rethinking of the discipline of automatic control to incorporate aspects of machine learning and optimization, in order to meet the new challenges arising. While control theory has been firmly rooted in tradition of model-based design, the availability and scale of data (both temporal and spatial) will require rethinking of the foundations of this discipline. From a machine learning perspective, one of the main challenges going forward is to go beyond pattern recognition and address problems in data driven control and optimization of dynamical processes. This course will provide the students with an introduction to topics at the intersection of learning and control theory, placing them in the appropriate historical context of system identification and adaptive control. Repeatability: No Additional Fee: Yes

Code

MECE 6362

Credits

3

Subject

MECE

Programs That Include This Course

• Master's Master of Science in Aerospace Engineering